Repository: kaneelgit/Trading-strategy-
Branch: main
Commit: 89233b84bad9
Files: 33
Total size: 110.0 KB

Directory structure:
gitextract_uysqdcle/

├── .ipynb_checkpoints/
│   └── crypto-checkpoint.ipynb
├── .vscode/
│   └── settings.json
├── README.md
├── backtester.py
├── backtester_ape.py
├── companies.csv
├── data_science/
│   ├── create_figures.py
│   └── stats.py
├── models/
│   ├── lr_inference.py
│   └── lr_run_training.py
├── results/
│   ├── LR_v1_predict_0.7_3/
│   │   ├── history_df.csv
│   │   ├── params
│   │   ├── results_summary
│   │   └── running_gains_df.csv
│   ├── LR_v1_predict_0.95_21/
│   │   ├── history_df.csv
│   │   ├── params
│   │   ├── results_summary
│   │   └── running_gains_df.csv
│   ├── LR_v1_predict_0.9_10/
│   │   ├── history_df.csv
│   │   ├── params
│   │   ├── results_summary
│   │   └── running_gains_df.csv
│   ├── LR_v1_predict_1_1/
│   │   ├── history_df.csv
│   │   ├── params
│   │   ├── results_summary
│   │   └── running_gains_df.csv
│   └── model_result_summary.csv
├── saved_models/
│   ├── lr_v1.sav
│   ├── lr_v2.sav
│   ├── scaler_v1.sav
│   └── scaler_v2.sav
└── stock_utils/
    ├── simulator.py
    └── stock_utils.py

================================================
FILE CONTENTS
================================================

================================================
FILE: .ipynb_checkpoints/crypto-checkpoint.ipynb
================================================
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "84309d53",
   "metadata": {},
   "outputs": [],
   "source": [
    "from td.client import TDClient\n",
    "import requests, time, re, os\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import pickle as pkl\n",
    "import numpy as np\n",
    "import datetime\n",
    "plt.style.use('grayscale')\n",
    "\n",
    "from scipy import linalg\n",
    "import math\n",
    "from datetime import datetime\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "\n",
    "import time\n",
    "from datetime import datetime\n",
    "import yfinance as yf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "48b0cba2",
   "metadata": {},
   "outputs": [],
   "source": [
    "bit = yf.Ticker('ETH-USD')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "b7128fa8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>Dividends</th>\n",
       "      <th>Stock Splits</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2021-11-13</th>\n",
       "      <td>4699.282227</td>\n",
       "      <td>4700.36377</td>\n",
       "      <td>4585.673828</td>\n",
       "      <td>4681.838867</td>\n",
       "      <td>14937333760</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Open        High          Low        Close       Volume  \\\n",
       "Date                                                                         \n",
       "2021-11-13  4699.282227  4700.36377  4585.673828  4681.838867  14937333760   \n",
       "\n",
       "            Dividends  Stock Splits  \n",
       "Date                                 \n",
       "2021-11-13          0             0  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "bit.history(period = '1m')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5db65814",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}


================================================
FILE: .vscode/settings.json
================================================
{
    "jupyter.jupyterServerType": "local"
}

================================================
FILE: README.md
================================================
# Trading-strategy-
Here I test a simple ML trading strategy

## Please note
- I have commented out the paths in the code. If you use code you'd have to correct them accordingly. 
- You will need to create a TDA developer account (https://developer.tdameritrade.com/apis) and get the API key in order to download the data. I have left this blank in the code where I used to download data. 

The blog article with results --> (https://medium.com/analytics-vidhya/how-im-using-machine-learning-to-trade-in-the-stock-market-3ba981a2ffc2)

Some results - 

Predicted buying opportunities

![1_2rdETRDZHCg4NqnIaXDWDA](https://user-images.githubusercontent.com/85404022/156928802-094d90c1-8ae6-491c-aea3-0672c3b032de.png)

Model comparison with the S&P 500 gains in 2021

![1_ZjoDR8c7fDGqMKXyRIbfpw](https://user-images.githubusercontent.com/85404022/156928807-9e94e6b8-0ce4-4ea1-8aad-bf1771ca1b3b.png)


================================================
FILE: backtester.py
================================================
"""
stock backtester to test the model given a dataset. 
author - Kaneel Senevirathne
date - 1/13/2022
"""

import numpy as np
from stock_utils.simulator import simulator
from stock_utils.stock_utils import get_stock_price
from models import lr_inference
from datetime import datetime
from datetime import timedelta
from td.client import TDClient
import pandas as pd
from models.lr_inference import LR_v1_predict, LR_v1_sell
import warnings
from collections import OrderedDict
warnings.filterwarnings("ignore")
import os
import pickle
from tqdm import tqdm

class backtester(simulator):

    def __init__(self, stocks_list, model, capital, start_date, end_date, threshold = 0.99, sell_perc = 0.04, hold_till = 5,\
         stop_perc = 0.005):
        
        super().__init__(capital) #initialize simulator

        self.stocks = stocks_list
        self.model = model
        self.start_date = start_date
        self.day = start_date
        self.end_date = end_date  
        self.status = 'buy' #the status says if the backtester is in buy mode or sell mode
        self.threshold = threshold
        self.sell_perc = sell_perc
        self.hold_till = hold_till
        self.stop_perc = stop_perc

        #current directory
        current_dir = os.getcwd()
        results_dir = os.path.join(current_dir, 'results')
        folder_name = f'{str(self.model.__name__)}_{self.threshold}_{self.hold_till}'
        self.folder_dir = os.path.join(results_dir, folder_name)
        if not os.path.exists(self.folder_dir):
            #create a new folder
            os.makedirs(self.folder_dir)
      
    def backtest(self):
        """
        start backtesting
        """
        delta = timedelta(days = 1)
        
        #progress bar to track progress
        total_days = (self.end_date - self.start_date).days
        d = 0
        pbar = tqdm(desc = 'Progress', total = total_days)

        while self.day <= self.end_date:
            
            #daily scanner dict
            self.daily_scanner = {}  
            if self.status == 'buy':
                #scan stocks for the day
                self.scanner()
                if list(self.daily_scanner.keys()) != []:
                    recommended_stock = list(self.daily_scanner.keys())[0]
                    recommended_price = list(self.daily_scanner.values())[0][2]
                    self.buy(recommended_stock, recommended_price, self.day) #buy stock
                    # print(f'Bought {recommended_stock} for {recommended_price} on the {self.day}')
                    self.status = 'sell' #change the status to sell
                else:
                    # print('No recommendations')
                    pass
            else: #if the status is sell
                #get stock price on the day
                stocks = [key for key in self.buy_orders.keys()]
                for s in stocks:
                    recommended_action, current_price = LR_v1_sell(s, self.buy_orders[s][3], self.buy_orders[s][0], self.day, \
                        self.sell_perc, self.hold_till, self.stop_perc)
                    if recommended_action == "SELL":
                        # print(f'Sold {s} for {current_price} on {self.day}')
                        self.sell(s, current_price, self.buy_orders[s][1], self.day)
                        self.status = 'buy'              
            #go to next day
            self.day += delta
            d += 1
            pbar.update(1)
        pbar.close()
        #sell the final stock and print final capital also print stock history 
        self.print_bag()
        self.print_summary() 
        self.save_results()      
        return

    def get_stock_data(self, stock, back_to = 40):
        """
        this function queries to td database and get data of a particular stock on a given day back to certain amount of days
        (default is 30). 
        """
        #get start and end dates
        end = self.day
        start = self.day - timedelta(days = back_to)        
        # prediction, prediction_thresholded, close_price = LR_v1_predict(stock, start, end, threshold = 0.5)
        prediction, prediction_thresholded, close_price = self.model(stock, start, end, self.threshold)
        return prediction[0], prediction_thresholded, close_price

    def scanner(self):
        """
        scan the stocks to find good stocks
        """
        for stock in self.stocks:
            try:#to ignore the stock if no data is available. #for staturdays or sundays etc
                prediction, prediction_thresholded, close_price = self.get_stock_data(stock)
                #if prediction greater than
                if prediction_thresholded < 1: #if prediction is zero
                    self.daily_scanner[stock] = (prediction, prediction_thresholded, close_price)
            except:
                pass

        def take_first(elem):
            return elem[1]

        self.daily_scanner = OrderedDict(sorted(self.daily_scanner.items(), key = take_first, reverse = True))

    def save_results(self):
        """
        save history dataframe create figures and save
        """
        #save csv file
        results_df_path = os.path.join(self.folder_dir, 'history_df.csv')
        self.history_df.to_csv(results_df_path, index = False)
        
        #save params and results summary
        results_summary_path = os.path.join(self.folder_dir, 'results_summary')
        results_summary = [self.initial_capital, self.total_gain]
        params_path = os.path.join(self.folder_dir, 'params')
        params = [self.threshold, self.hold_till, self.sell_perc, self.stop_perc, self.start_date, self.end_date]
        
        with open(results_summary_path, 'wb') as fp:
            pickle.dump(results_summary, fp)
        with open(params_path, 'wb') as fp:
            pickle.dump(params, fp)

if __name__ == "__main__":
    #stocks list
    dow = ['AXP', 'AMGN', 'AAPL', 'BA', 'CAT', 'CSCO', 'CVX', 'GS', 'HD', 'HON', 'IBM', 'INTC',\
        'JNJ', 'KO', 'JPM', 'MCD', 'MMM', 'MRK', 'MSFT', 'NKE', 'PG', 'TRV', 'UNH',\
        'CRM', 'VZ', 'V', 'WBA', 'WMT', 'DIS']
    other = ['AMD', 'MU', 'ABT', 'AAL', 'UAL', 'DAL', 'ANTM', 'ATVI', 'BAC', 'PNC', 'C', 'EBAY', 'AMZN', 'GOOG', 'FB', 'SNAP', 'TWTR'\
        'FDX', 'MCD', 'PEP', ]

    stocks = list(np.unique(dow + other))
    back = backtester(dow, LR_v1_predict, 3000, datetime(2021, 1, 1), datetime(2021, 12, 31), threshold = 0.9, sell_perc = 0.03, hold_till = 10,\
        stop_perc = 0.03)
    back.backtest()

    


    


================================================
FILE: backtester_ape.py
================================================
"""
stock backtester to test the model given a dataset. 
author - Kaneel Senevirathne
date - 1/13/2022
"""

import numpy as np
from stock_utils.simulator import simulator
from stock_utils.stock_utils import get_stock_price
from models import lr_inference
from datetime import datetime
from datetime import timedelta
from td.client import TDClient
import pandas as pd
from models.lr_inference import LR_v1_predict, LR_v1_sell
import warnings
from collections import OrderedDict
warnings.filterwarnings("ignore")
import os
import pickle
from tqdm import tqdm

class backtester(simulator):

    def __init__(self, stocks_list, model, capital, start_date, end_date, threshold = 0.99, sell_perc = 0.04, hold_till = 5,\
         stop_perc = 0.005):
        
        super().__init__(capital) #initialize simulator

        self.stocks = stocks_list
        self.model = model
        self.start_date = start_date
        self.day = start_date
        self.end_date = end_date  
        self.status = 'buy' #the status says if the backtester is in buy mode or sell mode
        self.threshold = threshold
        self.sell_perc = sell_perc
        self.hold_till = hold_till
        self.stop_perc = stop_perc

        #current directory
        current_dir = os.getcwd()
        results_dir = os.path.join(current_dir, 'results')
        folder_name = f'{str(self.model.__name__)}_{self.threshold}_{self.hold_till}'
        self.folder_dir = os.path.join(results_dir, folder_name)
        if not os.path.exists(self.folder_dir):
            #create a new folder
            os.makedirs(self.folder_dir)
      
    def backtest(self):
        """
        start backtesting
        """
        delta = timedelta(days = 1)
        
        #progress bar to track progress
        total_days = (self.end_date - self.start_date).days
        d = 0
        pbar = tqdm(desc = 'Progress', total = total_days)

        while self.day <= self.end_date:
            
            #daily scanner dict
            self.daily_scanner = {}  
            if self.status == 'buy':
                #scan stocks for the day
                self.scanner()
                if list(self.daily_scanner.keys()) != []:
                    recommended_stock = list(self.daily_scanner.keys())[0]
                    recommended_price = list(self.daily_scanner.values())[0][2]
                    self.buy(recommended_stock, recommended_price, self.day) #buy stock
                    # print(f'Bought {recommended_stock} for {recommended_price} on the {self.day}')
                    self.status = 'sell' #change the status to sell
                else:
                    # print('No recommendations')
                    pass
            else: #if the status is sell
                #get stock price on the day
                stocks = [key for key in self.buy_orders.keys()]
                for s in stocks:
                    recommended_action, current_price = LR_v1_sell(s, self.buy_orders[s][3], self.buy_orders[s][0], self.day, \
                        self.sell_perc, self.hold_till, self.stop_perc)

                    if np.random.choice([0, 1]) == 1: #randomly sell
                        # print(f'Sold {s} for {current_price} on {self.day}')
                        self.sell(s, current_price, self.buy_orders[s][1], self.day)
                        self.status = 'buy'              
            #go to next day
            self.day += delta
            d += 1
            pbar.update(1)
        pbar.close()
        #sell the final stock and print final capital also print stock history 
        self.print_bag()
        self.print_summary() 
        self.save_results()      
        return

    def get_stock_data(self, stock, back_to = 40):
        """
        this function queries to td database and get data of a particular stock on a given day back to certain amount of days
        (default is 30). 
        """
        #get start and end dates
        end = self.day
        start = self.day - timedelta(days = back_to)        
        # prediction, prediction_thresholded, close_price = LR_v1_predict(stock, start, end, threshold = 0.5)
        prediction, prediction_thresholded, close_price = self.model(stock, start, end, self.threshold)
        return prediction[0], prediction_thresholded, close_price

    def scanner(self):
        """
        scan the stocks to find good stocks
        """
        stock = np.random.choice(self.stocks)
        prediction, prediction_thresholded, close_price = self.get_stock_data(stock)
        self.daily_scanner[stock] = (prediction, prediction_thresholded, close_price)
            
    def save_results(self):
        """
        save history dataframe create figures and save
        """
        #save csv file
        results_df_path = os.path.join(self.folder_dir, 'history_df.csv')
        self.history_df.to_csv(results_df_path, index = False)
        
        #save params and results summary
        results_summary_path = os.path.join(self.folder_dir, 'results_summary')
        results_summary = [self.initial_capital, self.total_gain]
        params_path = os.path.join(self.folder_dir, 'params')
        params = [self.threshold, self.hold_till, self.sell_perc, self.stop_perc, self.start_date, self.end_date]
        
        with open(results_summary_path, 'wb') as fp:
            pickle.dump(results_summary, fp)
        with open(params_path, 'wb') as fp:
            pickle.dump(params, fp)

if __name__ == "__main__":
    #stocks list
    dow = ['AXP', 'AMGN', 'AAPL', 'BA', 'CAT', 'CSCO', 'CVX', 'GS', 'HD', 'HON', 'IBM', 'INTC',\
        'JNJ', 'KO', 'JPM', 'MCD', 'MMM', 'MRK', 'MSFT', 'NKE', 'PG', 'TRV', 'UNH',\
        'CRM', 'VZ', 'V', 'WBA', 'WMT', 'DIS']
    other = ['AMD', 'MU', 'ABT', 'AAL', 'UAL', 'DAL', 'ANTM', 'ATVI', 'BAC', 'PNC', 'C', 'EBAY', 'AMZN', 'GOOG', 'FB', 'SNAP', 'TWTR'\
        'FDX', 'MCD', 'PEP', ]

    stocks = list(np.unique(dow + other))
    back = backtester(dow, LR_v1_predict, 3000, datetime(2021, 1, 1), datetime(2021, 12, 31), threshold = 1, sell_perc = 0.03, hold_till = 1,\
        stop_perc = 0.03)
    back.backtest()

    


    


================================================
FILE: companies.csv
================================================
Ticker
AAPL
MSFT
GOOG
AMZN
TSLA
BRK-A
NVDA
FB
V
JPM
UNH
JNJ
WMT
PG
BAC
MA
HD
XOM
DIS
KO
PFE
ABBV
CVX
AVGO
CSCO
PEP
LLY
VZ
COST
NKE
WFC
CMCSA
TMO
ABT
ADBE
ORCL
CRM
MRK
AMD
DHR
MCD
QCOM
INTC
UPS
NFLX
T
MS
PM
SCHW
UNP
TMUS
TXN
AXP
BMY
NEE
LOW
RTX
INTU
CVS
C
HON
AMGN
PYPL
BA
AMAT
GS
COP
BLK
IBM
NOW
DE
SBUX
EL
ANTM
PLD
ABNB
LMT
AMT
GE
BKNG
CHTR
CAT
MU
ISRG
SYK
TGT
MO
SPGI
MDLZ
ZTS
BX
USB
CME
PNC
MMM
ADI
ADP
SNOW
TFC
LRCX
DUK
MMC
GILD
CSX
BDX
HCA
CI
TJX
CCI
F
ICE
GM
SHW
SO
REGN
ITW
EW
CL
UBER
PSA
EOG
D
COF
ATVI
EQIX
PGR
FISV
NSC
BSX
FCX
NOC
GD
MCO
SNAP
VRTX
WM
MRNA
FIS
FDX
MRVL
MET
MAR
RIVN
SLB
EMR
PXD
WDAY
KDP
SQ
KLAC
HUM
NEM
APD
SPG
SCCO
LBSI
ECL


================================================
FILE: data_science/create_figures.py
================================================
import pickle
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import os
from datetime import timedelta
import seaborn as sns

class create_figures:

    def __init__(self, model_name, threshold, hold_till):
        
        self.model = model_name
        self.threshold = threshold
        self.hold_till = hold_till
        
        results_dir = ## '\\results' folder directory
        self.folder_name = f'{str(self.model)}_{self.threshold}_{self.hold_till}'
        self.folder_dir = os.path.join(results_dir, self.folder_name)

        history_df_path = os.path.join(self.folder_dir, 'history_df.csv')
        self.history_df = pd.read_csv(history_df_path)
        self.history_df['buy_date'] = pd.to_datetime(self.history_df['buy_date'])
        self.history_df['sell_date'] = pd.to_datetime(self.history_df['sell_date'])
        
        params_path = os.path.join(self.folder_dir, 'params')
        with open(params_path, 'rb') as fp:
            self.params = pickle.load(fp)
        
        results_summary_path = os.path.join(self.folder_dir, 'results_summary')
        with open(results_summary_path, 'rb') as fp:
            self.results_summary = pickle.load(fp)
        
        #get params from stored files
        self.initial_capital = self.results_summary[0]
        self.total_gain = self.results_summary[1]
        self.start_date = self.params[4]
        self.end_date = self.params[5]
        
        self.create_history_df()
        self.create_history_figure()
        self.gain_loss_plot()
        self.hold_hist()

    def create_history_df(self):
        """
        this function creates a dataframe from start date to end date
        """
        cols = ['Date', 'Stock', 'Gain', 'Total']
        self.running_gains_df = pd.DataFrame(columns = cols)
        #create a row with the start date - 1 with the starting balance
        self.running_gains_df = self.running_gains_df.append({'Date': self.start_date - timedelta(days = 1), 'Stock': np.nan, 'Gain': \
            np.nan, 'Total': self.initial_capital}, ignore_index = True)
        values_total = self.initial_capital #start balance
        
        #create date range
        def date_range(start, end):
            delta = end - start  # as timedelta
            days = [start + timedelta(days=i) for i in range(delta.days + 1)]
            return days
        
        days = date_range(self.start_date, self.end_date)
        
        for day in days:
            #find if data is available. 1 if available 0 if not
            available = self.history_df[self.history_df['buy_date'] == day].values.shape[0]
            if available > 0:
                values = self.history_df.loc[self.history_df['buy_date'] == day].reset_index(drop = True)
                values_date = day
                values_stock = values['stock'][0]
                values_gain = values['net_gain'][0]
                values_total = values_total + values_gain
                #dict to append
                dict_ = {'Date': values_date, 'Stock': values_stock, 'Gain': values_gain, 'Total': values_total}
                self.running_gains_df = self.running_gains_df.append(dict_, ignore_index = True)
            else:
                dict_ = {'Date': day, 'Stock': np.nan, 'Gain': np.nan, 'Total': values_total}
                self.running_gains_df = self.running_gains_df.append(dict_, ignore_index = True)
        
        #save the running gains df
        self.running_gains_df.to_csv(f'{self.folder_dir}/running_gains_df.csv', index = False)

    def create_history_figure(self):
        """
        plot the running gains
        """
        plt.figure(figsize = (10, 6))
        plt.plot(self.running_gains_df['Date'], self.running_gains_df['Total'])
        plt.xlabel('Time (days)', fontsize = '6')
        plt.ylabel('Total Balance ($)')
        plt.xticks(rotation = 45)
        # plt.show()
        fig_path = os.path.join(self.folder_dir, 'total_balance_history.jpg')
        plt.savefig(fig_path)

    def gain_loss_plot(self):
        """
        a bar plot with gains and losses on the day
        """
        positives = self.running_gains_df[self.running_gains_df['Gain'] > 0]
        negatives = self.running_gains_df[self.running_gains_df['Gain'] < 0]
        plt.figure(figsize = (10, 6))
        plt.bar(positives['Date'], positives['Gain'], color = 'g', width = 1.5, label = 'wins')
        plt.bar(negatives['Date'], negatives['Gain'], color = 'r', width = 1.5, label = 'losses')
        plt.axhline(linewidth = 1, color = 'k')
        plt.legend()
        plt.xlabel('Time (days)', fontsize = '6')
        plt.ylabel('Gain ($)')
        plt.xticks(rotation = 45)
        # plt.show()
        fig_path = os.path.join(self.folder_dir, 'gain_loss.jpg')
        plt.savefig(fig_path)

    def hold_hist(self):
        """
        This function creates a histogram with buy times and color code it with winner or loser
        """
        #create columns
        df = self.history_df
        df['winner_bool'] = ['win' if x > 0 else 'loss' for x in df.net_gain]
        df['held_time'] = [(t2 - t1).days for t2, t1 in zip(df['sell_date'], df['buy_date'])]

        plt.figure(figsize = (10, 6))
        sns.histplot(x = 'held_time', data = df, hue = 'winner_bool', bins = 100)
        plt.xticks(rotation = 45)
        plt.xlabel('Held time (days)')
        # plt.show()
        fig_path = os.path.join(self.folder_dir, 'held_time_histogram.jpg')
        plt.savefig(fig_path)

if __name__ == '__main__':
    create_figures('LR_v1_predict', 1, 1)

================================================
FILE: data_science/stats.py
================================================
import pickle
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import os
from datetime import timedelta
import seaborn as sns

class create_stats:

    def __init__(self, model_name, threshold, hold_till):
        
        self.model = model_name
        self.threshold = threshold
        self.hold_till = hold_till
        
        results_dir = #add results directory
        self.folder_name = f'{str(self.model)}_{self.threshold}_{self.hold_till}'
        self.folder_dir = os.path.join(results_dir, self.folder_name)

        history_df_path = os.path.join(self.folder_dir, 'history_df.csv')
        self.history_df = pd.read_csv(history_df_path)
        self.history_df['buy_date'] = pd.to_datetime(self.history_df['buy_date'])
        self.history_df['sell_date'] = pd.to_datetime(self.history_df['sell_date'])
        
        params_path = os.path.join(self.folder_dir, 'params')
        with open(params_path, 'rb') as fp:
            self.params = pickle.load(fp)
        
        results_summary_path = os.path.join(self.folder_dir, 'results_summary')
        with open(results_summary_path, 'rb') as fp:
            self.results_summary = pickle.load(fp)
        
        #get params from stored files
        self.initial_capital = self.results_summary[0]
        self.total_gain = self.results_summary[1]
        self.start_date = self.params[4]
        self.end_date = self.params[5]

        self.calculate_stats()
        self.save_stats()
    
    def calculate_stats(self):

        #calculate total percentage win
        self.total_percentage = np.round(self.total_gain/self.initial_capital * 100, 2)
        #total gains
        self.total_gains = np.round(self.history_df[self.history_df['net_gain'] > 0]['net_gain'].sum(), 2)
        self.maximum_gain = np.round(self.history_df[self.history_df['net_gain'] > 0]['net_gain'].max(), 2)
        #total losses
        self.total_losses = np.round(self.history_df[self.history_df['net_gain'] < 0]['net_gain'].sum(), 2)
        self.maximum_loss = np.round(self.history_df[self.history_df['net_gain'] < 0]['net_gain'].min())
    
    def save_stats(self):

        df = pd.read_csv(## add results/model_result_summary.csv path)

        results_dict = {'Model': f'{self.model}_{self.threshold}_{self.hold_till}',\
            'Gains': self.total_gains,
            'Losses': self.total_losses,
            'Profit': np.round(self.total_gain, 2),
            'Profit Percentage': self.total_percentage,
            'Maximum Gain': self.maximum_gain,
            'Maximum Loss': self.maximum_loss}
        df = df.append(results_dict, ignore_index = True)
        df.to_csv(## add path results/model_result_summary.csv')        

if __name__ == "__main__":
    cs = create_stats('LR_v1_predict', 1, 1)

================================================
FILE: models/lr_inference.py
================================================
"""
stock backtester to test the model given a dataset. 
author - Kaneel Senevirathne
date - 1/13/2022
"""

from doctest import OutputChecker
import numpy as np
import pickle
from sklearn.linear_model import LogisticRegression
from stock_utils.stock_utils import timestamp, create_train_data, get_data, create_test_data_lr, get_stock_price
from datetime import timedelta
import time

def load_LR(model_version):

    file = #add path to the saved models folder and then model version 'eg: f'//saved_models//lr_{model_version}.sav'
    loaded_model = pickle.load(open(file, 'rb'))

    return loaded_model

def load_scaler(model_version):

    file = ## add path to //saved_models//scaler_{model_version}.sav'
    loaded_model = pickle.load(open(file, 'rb'))

    return loaded_model

def _threshold(probs, threshold):
    """
    Inputs the probability and returns 1 or 0 based on the threshold
    """
    prob_thresholded = [0 if x > threshold else 1 for x in probs[:, 0]]

    return np.array(prob_thresholded)


def LR_v1_predict(stock, start_date, end_date, threshold = 0.98):
    """
    this function predict given the data
    """
    #create model and scaler instances
    scaler = load_scaler('v2')
    lr = load_LR('v2')
    #create input
    data = create_test_data_lr(stock, start_date, end_date)
    #get close price of final date
    close_price = data['close'].values[-1]
    #get input data to model
    input_data = data[['volume', 'normalized_value', '3_reg', '5_reg', '10_reg', '20_reg']]
    input_data = input_data.to_numpy()[-1].reshape(1, -1)
    #scale input data
    input_data_scaled = scaler.transform(input_data)
    prediction = lr._predict_proba_lr(input_data_scaled)
    prediction_thresholded = _threshold(prediction, threshold)
   
    return prediction[:, 0], prediction_thresholded[0], close_price

def LR_v1_sell(stock, buy_date, buy_price, todays_date, sell_perc = 0.1, hold_till = 3, stop_perc = 0.05):
    """
    gets stock price. recommnd to sell if the stock price is higher sell_perc * buy_price + buy_price
    stock - stock ticker symbol
    buy_date - the date the stock was bought
    todays_date - date today
    sell_perc - sell percentage 
    hold_till - how many days to hold from today
    """
    current_price = get_stock_price(stock, todays_date) #current stock value
    sell_price = buy_price + buy_price * sell_perc
    stop_price = buy_price - buy_price * stop_perc
    sell_date = buy_date + timedelta(days = hold_till) #the day to sell 
    time.sleep(1) #to make sure the requested transactions per seconds is not exeeded.
    #some times it returns current price as none
    if (current_price is not None) and ((current_price < stop_price) or (current_price >= sell_price) or (todays_date >= sell_date)):
        return "SELL", current_price #if criteria is met recommend to sell
    else:
        return "HOLD", current_price #if crieteria is not met hold the stock







================================================
FILE: models/lr_run_training.py
================================================
"""
LR training 
author - Kaneel Senevirathne
date - 1/13/2022
"""

from td.client import TDClient
import requests, time, re, os
import matplotlib.pyplot as plt
import pandas as pd
import pickle as pkl
import numpy as np
import datetime
plt.style.use('grayscale')

from scipy import linalg
import math
from datetime import datetime
import warnings
warnings.filterwarnings("ignore")

import time
from datetime import datetime
import os
import sys
import pickle

#append path
current_dir = os.getcwd()
sys.path.append(current_dir)

from stock_utils import stock_utils
import sklearn 
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler, StandardScaler
from sklearn.linear_model import LogisticRegression

from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
import seaborn as sns

class LR_training:

    def __init__(self, model_version, threshold = 0.98, start_date = None, end_date = None):

        self.model_version = model_version
        self.threshold = threshold
        
        if start_date:
            self.start_date = start_date
        if end_date:
            self.end_date = end_date

        #get stock ticker symbols
        dow = ['AXP', 'AMGN', 'AAPL', 'BA', 'CAT', 'CSCO', 'CVX', 'GS', 'HD', 'HON', 'IBM', 'INTC',\
        'JNJ', 'KO', 'JPM', 'MCD', 'MMM', 'MRK', 'MSFT', 'NKE', 'PG', 'TRV', 'UNH',\
        'CRM', 'VZ', 'V', 'WBA', 'WMT', 'DIS']
        sp500 = #use pandas to open the companies csv
        sp = list(sp500['Ticker'])
        stocks = dow + sp[:20]
        self.stocks = list(np.unique(stocks))

        #main dataframe
        self.main_df = pd.DataFrame(columns = ['volume', 'normalized_value', '3_reg', '5_reg', '10_reg', '20_reg', 'target'])

        #init models
        self.scaler = MinMaxScaler()
        self.lr = LogisticRegression()

        #run logistic regresion
        self.fetch_data()
        self.create_train_test()
        self.fit_model()
        self.confusion_matrix()
        self.save_model()

    def fetch_data(self):
        """
        get train and test data
        """ 
        for stock in self.stocks:
            try: 
                df = stock_utils.create_train_data(stock, n = 10)
                self.main_df = self.main_df.append(df)
            except:
                pass
        print(f'{len(self.main_df)} samples were fetched from the database..')

    def create_train_test(self):
        """
        create train and test data
        """
        self.main_df = self.main_df.sample(frac = 1, random_state = 3). reset_index(drop = True)
        self.main_df['target'] = self.main_df['target'].astype('category')
        
        y = self.main_df.pop('target').to_numpy()
        y = y.reshape(y.shape[0], 1)
        x = self.scaler.fit_transform(self.main_df)

        #test train split
        self.train_x, self.test_x, self.train_y, self.test_y = train_test_split(x, y, \
            test_size = 0.05, random_state = 50, shuffle = True)

        print('Created test and train data...')

    def fit_model(self):

        print('Training model...')
        self.lr.fit(self.train_x, self.train_y)
        
        #predict the test data
        self.predictions = self.lr.predict(self.test_x)
        self.score = self.lr.score(self.test_x, self.test_y)
        print(f'Logistic regression model score: {self.score}')

        #preds with threshold
        self.predictions_proba = self.lr._predict_proba_lr(self.test_x)
        self.predictions_proba_thresholded = self._threshold(self.predictions_proba, self.threshold)
      
    def confusion_matrix(self):
        cm = confusion_matrix(self.test_y, self.predictions)
        self.cmd = ConfusionMatrixDisplay(cm)
        
        cm_thresholded = confusion_matrix(self.test_y, self.predictions_proba_thresholded)
        self.cmd_thresholded = ConfusionMatrixDisplay(cm_thresholded)

        
    def _threshold(self, predictions, threshold):

        prob_thresholded = [0 if x > threshold else 1 for x in predictions[:, 0]]

        return np.array(prob_thresholded)

    def save_model(self):

        #save models
        saved_models_dir = os.path.join(os.getcwd(), 'saved_models')
        model_file = f'lr_{self.model_version}.sav'
        model_dir = os.path.join(saved_models_dir, model_file)
        pickle.dump(self.lr, open(model_dir, 'wb'))

        scaler_file = f'scaler_{self.model_version}.sav'
        scaler_dir = os.path.join(saved_models_dir, scaler_file)
        pickle.dump(self.scaler, open(scaler_dir, 'wb'))

        print(f'Saved the model and scaler in {saved_models_dir}')
        cm_path = os.path.join(os.getcwd(), 'results\Confusion Matrices')
        
        #save cms
        plt.figure()
        self.cmd.plot()
        plt.savefig(f'{cm_path}\\cm_{self.model_version}.jpg')

        plt.figure()
        self.cmd_thresholded.plot()
        plt.savefig(f'{cm_path}\\cm_thresholded_{self.model_version}.jpg')
        print(f'Figures saved in {cm_path}')

import argparse

if __name__ == "__main__":
    run_lr = LR_training('v2')



================================================
FILE: results/LR_v1_predict_0.7_3/history_df.csv
================================================
stock,buy_price,n_shares,sell_price,net_gain,buy_date,sell_date
BA,214.06,14,214.06,0.0,2021-01-01,2021-01-04
BA,202.72,14,211.63,124.73999999999995,2021-01-05,2021-01-06
MSFT,212.25,14,218.29,84.55999999999989,2021-01-07,2021-01-08
JNJ,160.04,20,159.37,-13.39999999999975,2021-01-09,2021-01-12
INTC,56.95,56,59.25,128.79999999999984,2021-01-14,2021-01-15
CRM,213.14,15,213.14,0.0,2021-01-16,2021-01-19
PG,133.6,24,131.93,-40.0799999999997,2021-01-20,2021-01-21
HON,205.23,16,202.25,-47.679999999999836,2021-01-22,2021-01-23
V,202.02,16,200.98,-16.640000000000327,2021-01-24,2021-01-26
HON,201.06,16,199.38,-26.88000000000011,2021-01-27,2021-01-28
V,198.22,16,193.25,-79.51999999999998,2021-01-29,2021-01-30
V,193.25,16,198.36,81.76000000000022,2021-01-31,2021-02-02
PG,128.79,24,129.17,9.11999999999989,2021-02-03,2021-02-09
HD,276.77,11,278.69,21.120000000000175,2021-02-10,2021-02-11
PG,128.33,25,127.62,-17.7500000000002,2021-02-12,2021-02-13
VZ,54.2,59,54.15,-2.9500000000002515,2021-02-14,2021-02-17
AXP,128.56,24,135.95,177.35999999999967,2021-02-18,2021-02-23
JNJ,160.44,21,162.59,45.15000000000012,2021-02-24,2021-02-25
HD,255.25,13,258.34,40.169999999999675,2021-02-26,2021-02-27
AAPL,121.26,28,127.79,182.84000000000003,2021-02-28,2021-03-02
CRM,213.47,17,211.96,-25.669999999999845,2021-03-03,2021-03-11
VZ,55.51,65,55.63,7.800000000000296,2021-03-12,2021-03-15
WMT,133.43,27,132.28,-31.050000000000153,2021-03-16,2021-03-18
WMT,130.01,27,131.74,46.71000000000049,2021-03-19,2021-03-20
V,206.9,17,213.53,112.70999999999992,2021-03-21,2021-03-27
GS,327.39,11,325.73,-18.25999999999965,2021-03-28,2021-03-30
MRK,76.96,48,77.09,6.240000000000464,2021-03-31,2021-04-03
KO,52.51,71,52.81,21.300000000000303,2021-04-04,2021-04-06
CVX,103.58,36,102.92,-23.759999999999877,2021-04-07,2021-04-11
WBA,54.18,69,54.7,35.880000000000216,2021-04-12,2021-04-13
NKE,133.54,28,132.26,-35.84000000000003,2021-04-14,2021-04-15
JNJ,160.39,23,162.24,42.55000000000052,2021-04-16,2021-04-17
WBA,53.3,71,53.02,-19.879999999999576,2021-04-18,2021-04-25
PG,133.94,28,131.26,-75.04000000000019,2021-04-26,2021-04-27
CSCO,51.37,71,51.11,-18.45999999999986,2021-04-28,2021-04-29
AAPL,133.48,27,131.46,-54.53999999999951,2021-04-30,2021-05-01
CVX,103.07,35,106.11,106.40000000000022,2021-05-02,2021-05-05
CRM,215.4,17,218.05,45.0500000000001,2021-05-06,2021-05-07
CRM,216.5,17,213.89,-44.37000000000023,2021-05-08,2021-05-11
TRV,156.69,23,153.75,-67.61999999999995,2021-05-12,2021-05-13
CRM,211.86,17,221.34,161.15999999999983,2021-05-14,2021-05-20
VZ,56.79,67,56.91,8.039999999999829,2021-05-21,2021-05-24
HD,314.84,12,316.75,22.9200000000003,2021-05-25,2021-05-26
AMGN,238.55,16,235.31,-51.840000000000146,2021-05-27,2021-05-28
HD,318.91,11,311.01,-86.90000000000038,2021-05-29,2021-06-05
JNJ,165.97,22,164.84,-24.8599999999999,2021-06-06,2021-06-08
WMT,139.83,26,139.08,-19.5,2021-06-09,2021-06-10
CAT,225.73,16,220.7,-80.48000000000002,2021-06-11,2021-06-12
CAT,220.7,16,208.86,-189.4399999999996,2021-06-13,2021-06-21
CAT,213.21,15,219.34,91.94999999999993,2021-06-22,2021-06-25
MCD,232.42,15,231.09,-19.94999999999976,2021-06-26,2021-06-29
BA,235.76,14,239.56,53.20000000000016,2021-06-30,2021-07-01
CAT,216.71,16,217.76,16.799999999999727,2021-07-02,2021-07-06
AMGN,243.65,14,243.22,-6.0200000000000955,2021-07-07,2021-07-08
TRV,148.52,23,153.33,110.63000000000005,2021-07-09,2021-07-10
MRK,77.99,46,77.55,-20.239999999999895,2021-07-11,2021-07-13
BA,228.2,15,222.54,-84.89999999999995,2021-07-14,2021-07-22
MMM,199.07,17,200.49,24.14000000000027,2021-07-23,2021-07-24
AXP,173.18,20,172.61,-11.399999999999864,2021-07-25,2021-07-27
WBA,46.82,75,47.11,21.749999999999936,2021-07-28,2021-07-29
AMGN,242.46,14,233.99,-118.57999999999998,2021-07-30,2021-08-06
VZ,55.22,62,55.12,-6.200000000000088,2021-08-07,2021-08-10
MCD,233.45,14,235.55,29.40000000000032,2021-08-11,2021-08-12
V,231.79,15,232.65,12.900000000000205,2021-08-13,2021-08-16
DIS,175.83,19,174.74,-20.710000000000065,2021-08-18,2021-08-19
BA,212.16,16,212.67,8.159999999999854,2021-08-20,2021-08-23
VZ,55.42,62,55.01,-25.42000000000023,2021-08-24,2021-08-25
AMGN,221.59,15,222.78,17.849999999999966,2021-08-26,2021-08-28
HON,231.14,15,231.91,11.550000000000153,2021-08-29,2021-09-01
BA,218.12,15,220.83,40.65000000000012,2021-09-02,2021-09-03
WBA,51.29,68,51.29,0.0,2021-09-04,2021-09-07
MMM,185.58,18,187.89,41.57999999999953,2021-09-08,2021-09-09
AMGN,215.58,16,218.13,40.79999999999973,2021-09-10,2021-09-16
BA,213.36,16,213.36,0.0,2021-09-17,2021-09-20
AMGN,215.11,16,213.64,-23.520000000000437,2021-09-21,2021-09-23
UNH,408.03,8,407.08,-7.599999999999909,2021-09-24,2021-09-25
KO,53.89,66,53.02,-57.41999999999983,2021-09-26,2021-10-02
MRK,81.4,43,83.1,73.09999999999951,2021-10-03,2021-10-05
V,224.28,16,226.51,35.679999999999836,2021-10-06,2021-10-07
MMM,177.8,20,176.95,-17.000000000000455,2021-10-08,2021-10-09
VZ,53.24,67,52.27,-64.98999999999992,2021-10-10,2021-10-18
MRK,77.15,45,79.49,105.29999999999951,2021-10-19,2021-10-20
V,231.42,15,230.24,-17.699999999999676,2021-10-21,2021-10-22
BA,212.97,17,212.87,-1.6999999999999034,2021-10-23,2021-10-26
MCD,236.42,15,250.58,212.40000000000038,2021-10-27,2021-11-02
TRV,158.82,24,160.25,34.320000000000164,2021-11-03,2021-11-04
V,208.78,18,216.67,142.01999999999975,2021-11-05,2021-11-06
GS,407.08,9,405.35,-15.569999999999652,2021-11-07,2021-11-10
AAPL,147.92,27,153.49,150.39000000000058,2021-11-11,2021-11-18
TRV,156.03,26,152.53,-91.0,2021-11-19,2021-11-20
TRV,152.53,26,156.87,112.84000000000009,2021-11-21,2021-11-23
DIS,151.03,27,148.11,-78.83999999999966,2021-11-24,2021-11-27
AMGN,201.09,20,201.17,1.5999999999996817,2021-11-28,2021-12-03
CRM,258.32,15,258.75,6.450000000000102,2021-12-04,2021-12-07
INTC,52.57,78,51.75,-63.96000000000002,2021-12-08,2021-12-09
NKE,168.1,24,169.06,23.04000000000019,2021-12-10,2021-12-11
CRM,266.03,15,252.93,-196.4999999999995,2021-12-12,2021-12-19
HD,387.98,9,390.47,22.410000000000082,2021-12-20,2021-12-22
TRV,154.69,25,154.65,-0.999999999999801,2021-12-23,2021-12-26
JPM,157.26,24,158.16,21.600000000000136,2021-12-27,2021-12-28


================================================
FILE: results/LR_v1_predict_0.7_3/running_gains_df.csv
================================================
Date,Stock,Gain,Total
2020-12-31,,,3000
2021-01-01,BA,0.0,3000.0
2021-01-02,,,3000.0
2021-01-03,,,3000.0
2021-01-04,,,3000.0
2021-01-05,BA,124.73999999999997,3124.74
2021-01-06,,,3124.74
2021-01-07,MSFT,84.55999999999989,3209.2999999999997
2021-01-08,,,3209.2999999999997
2021-01-09,JNJ,-13.39999999999975,3195.9
2021-01-10,,,3195.9
2021-01-11,,,3195.9
2021-01-12,,,3195.9
2021-01-13,,,3195.9
2021-01-14,INTC,128.79999999999984,3324.7
2021-01-15,,,3324.7
2021-01-16,CRM,0.0,3324.7
2021-01-17,,,3324.7
2021-01-18,,,3324.7
2021-01-19,,,3324.7
2021-01-20,PG,-40.0799999999997,3284.62
2021-01-21,,,3284.62
2021-01-22,HON,-47.67999999999984,3236.94
2021-01-23,,,3236.94
2021-01-24,V,-16.640000000000327,3220.2999999999997
2021-01-25,,,3220.2999999999997
2021-01-26,,,3220.2999999999997
2021-01-27,HON,-26.88000000000011,3193.4199999999996
2021-01-28,,,3193.4199999999996
2021-01-29,V,-79.51999999999998,3113.8999999999996
2021-01-30,,,3113.8999999999996
2021-01-31,V,81.76000000000022,3195.66
2021-02-01,,,3195.66
2021-02-02,,,3195.66
2021-02-03,PG,9.11999999999989,3204.7799999999997
2021-02-04,,,3204.7799999999997
2021-02-05,,,3204.7799999999997
2021-02-06,,,3204.7799999999997
2021-02-07,,,3204.7799999999997
2021-02-08,,,3204.7799999999997
2021-02-09,,,3204.7799999999997
2021-02-10,HD,21.12000000000017,3225.9
2021-02-11,,,3225.9
2021-02-12,PG,-17.7500000000002,3208.15
2021-02-13,,,3208.15
2021-02-14,VZ,-2.9500000000002515,3205.2
2021-02-15,,,3205.2
2021-02-16,,,3205.2
2021-02-17,,,3205.2
2021-02-18,AXP,177.35999999999967,3382.5599999999995
2021-02-19,,,3382.5599999999995
2021-02-20,,,3382.5599999999995
2021-02-21,,,3382.5599999999995
2021-02-22,,,3382.5599999999995
2021-02-23,,,3382.5599999999995
2021-02-24,JNJ,45.15000000000012,3427.7099999999996
2021-02-25,,,3427.7099999999996
2021-02-26,HD,40.16999999999968,3467.879999999999
2021-02-27,,,3467.879999999999
2021-02-28,AAPL,182.84000000000003,3650.7199999999993
2021-03-01,,,3650.7199999999993
2021-03-02,,,3650.7199999999993
2021-03-03,CRM,-25.669999999999845,3625.0499999999993
2021-03-04,,,3625.0499999999993
2021-03-05,,,3625.0499999999993
2021-03-06,,,3625.0499999999993
2021-03-07,,,3625.0499999999993
2021-03-08,,,3625.0499999999993
2021-03-09,,,3625.0499999999993
2021-03-10,,,3625.0499999999993
2021-03-11,,,3625.0499999999993
2021-03-12,VZ,7.800000000000296,3632.8499999999995
2021-03-13,,,3632.8499999999995
2021-03-14,,,3632.8499999999995
2021-03-15,,,3632.8499999999995
2021-03-16,WMT,-31.050000000000157,3601.7999999999993
2021-03-17,,,3601.7999999999993
2021-03-18,,,3601.7999999999993
2021-03-19,WMT,46.71000000000049,3648.5099999999998
2021-03-20,,,3648.5099999999998
2021-03-21,V,112.70999999999992,3761.22
2021-03-22,,,3761.22
2021-03-23,,,3761.22
2021-03-24,,,3761.22
2021-03-25,,,3761.22
2021-03-26,,,3761.22
2021-03-27,,,3761.22
2021-03-28,GS,-18.25999999999965,3742.96
2021-03-29,,,3742.96
2021-03-30,,,3742.96
2021-03-31,MRK,6.240000000000464,3749.2000000000007
2021-04-01,,,3749.2000000000007
2021-04-02,,,3749.2000000000007
2021-04-03,,,3749.2000000000007
2021-04-04,KO,21.300000000000303,3770.500000000001
2021-04-05,,,3770.500000000001
2021-04-06,,,3770.500000000001
2021-04-07,CVX,-23.75999999999988,3746.740000000001
2021-04-08,,,3746.740000000001
2021-04-09,,,3746.740000000001
2021-04-10,,,3746.740000000001
2021-04-11,,,3746.740000000001
2021-04-12,WBA,35.880000000000216,3782.6200000000013
2021-04-13,,,3782.6200000000013
2021-04-14,NKE,-35.84000000000003,3746.780000000001
2021-04-15,,,3746.780000000001
2021-04-16,JNJ,42.55000000000052,3789.3300000000017
2021-04-17,,,3789.3300000000017
2021-04-18,WBA,-19.879999999999576,3769.450000000002
2021-04-19,,,3769.450000000002
2021-04-20,,,3769.450000000002
2021-04-21,,,3769.450000000002
2021-04-22,,,3769.450000000002
2021-04-23,,,3769.450000000002
2021-04-24,,,3769.450000000002
2021-04-25,,,3769.450000000002
2021-04-26,PG,-75.04000000000019,3694.4100000000017
2021-04-27,,,3694.4100000000017
2021-04-28,CSCO,-18.45999999999986,3675.9500000000016
2021-04-29,,,3675.9500000000016
2021-04-30,AAPL,-54.53999999999951,3621.410000000002
2021-05-01,,,3621.410000000002
2021-05-02,CVX,106.40000000000022,3727.810000000002
2021-05-03,,,3727.810000000002
2021-05-04,,,3727.810000000002
2021-05-05,,,3727.810000000002
2021-05-06,CRM,45.0500000000001,3772.8600000000024
2021-05-07,,,3772.8600000000024
2021-05-08,CRM,-44.37000000000023,3728.490000000002
2021-05-09,,,3728.490000000002
2021-05-10,,,3728.490000000002
2021-05-11,,,3728.490000000002
2021-05-12,TRV,-67.61999999999995,3660.870000000002
2021-05-13,,,3660.870000000002
2021-05-14,CRM,161.15999999999983,3822.030000000002
2021-05-15,,,3822.030000000002
2021-05-16,,,3822.030000000002
2021-05-17,,,3822.030000000002
2021-05-18,,,3822.030000000002
2021-05-19,,,3822.030000000002
2021-05-20,,,3822.030000000002
2021-05-21,VZ,8.039999999999829,3830.070000000002
2021-05-22,,,3830.070000000002
2021-05-23,,,3830.070000000002
2021-05-24,,,3830.070000000002
2021-05-25,HD,22.9200000000003,3852.9900000000025
2021-05-26,,,3852.9900000000025
2021-05-27,AMGN,-51.84000000000015,3801.1500000000024
2021-05-28,,,3801.1500000000024
2021-05-29,HD,-86.90000000000038,3714.250000000002
2021-05-30,,,3714.250000000002
2021-05-31,,,3714.250000000002
2021-06-01,,,3714.250000000002
2021-06-02,,,3714.250000000002
2021-06-03,,,3714.250000000002
2021-06-04,,,3714.250000000002
2021-06-05,,,3714.250000000002
2021-06-06,JNJ,-24.8599999999999,3689.390000000002
2021-06-07,,,3689.390000000002
2021-06-08,,,3689.390000000002
2021-06-09,WMT,-19.5,3669.890000000002
2021-06-10,,,3669.890000000002
2021-06-11,CAT,-80.48000000000002,3589.410000000002
2021-06-12,,,3589.410000000002
2021-06-13,CAT,-189.4399999999996,3399.9700000000025
2021-06-14,,,3399.9700000000025
2021-06-15,,,3399.9700000000025
2021-06-16,,,3399.9700000000025
2021-06-17,,,3399.9700000000025
2021-06-18,,,3399.9700000000025
2021-06-19,,,3399.9700000000025
2021-06-20,,,3399.9700000000025
2021-06-21,,,3399.9700000000025
2021-06-22,CAT,91.94999999999992,3491.9200000000023
2021-06-23,,,3491.9200000000023
2021-06-24,,,3491.9200000000023
2021-06-25,,,3491.9200000000023
2021-06-26,MCD,-19.94999999999976,3471.9700000000025
2021-06-27,,,3471.9700000000025
2021-06-28,,,3471.9700000000025
2021-06-29,,,3471.9700000000025
2021-06-30,BA,53.20000000000016,3525.170000000003
2021-07-01,,,3525.170000000003
2021-07-02,CAT,16.799999999999727,3541.9700000000025
2021-07-03,,,3541.9700000000025
2021-07-04,,,3541.9700000000025
2021-07-05,,,3541.9700000000025
2021-07-06,,,3541.9700000000025
2021-07-07,AMGN,-6.020000000000096,3535.9500000000025
2021-07-08,,,3535.9500000000025
2021-07-09,TRV,110.63000000000004,3646.5800000000027
2021-07-10,,,3646.5800000000027
2021-07-11,MRK,-20.239999999999892,3626.340000000003
2021-07-12,,,3626.340000000003
2021-07-13,,,3626.340000000003
2021-07-14,BA,-84.89999999999995,3541.440000000003
2021-07-15,,,3541.440000000003
2021-07-16,,,3541.440000000003
2021-07-17,,,3541.440000000003
2021-07-18,,,3541.440000000003
2021-07-19,,,3541.440000000003
2021-07-20,,,3541.440000000003
2021-07-21,,,3541.440000000003
2021-07-22,,,3541.440000000003
2021-07-23,MMM,24.14000000000027,3565.580000000003
2021-07-24,,,3565.580000000003
2021-07-25,AXP,-11.399999999999864,3554.180000000003
2021-07-26,,,3554.180000000003
2021-07-27,,,3554.180000000003
2021-07-28,WBA,21.749999999999936,3575.930000000003
2021-07-29,,,3575.930000000003
2021-07-30,AMGN,-118.57999999999998,3457.350000000003
2021-07-31,,,3457.350000000003
2021-08-01,,,3457.350000000003
2021-08-02,,,3457.350000000003
2021-08-03,,,3457.350000000003
2021-08-04,,,3457.350000000003
2021-08-05,,,3457.350000000003
2021-08-06,,,3457.350000000003
2021-08-07,VZ,-6.200000000000088,3451.150000000003
2021-08-08,,,3451.150000000003
2021-08-09,,,3451.150000000003
2021-08-10,,,3451.150000000003
2021-08-11,MCD,29.40000000000032,3480.550000000003
2021-08-12,,,3480.550000000003
2021-08-13,V,12.900000000000205,3493.450000000003
2021-08-14,,,3493.450000000003
2021-08-15,,,3493.450000000003
2021-08-16,,,3493.450000000003
2021-08-17,,,3493.450000000003
2021-08-18,DIS,-20.710000000000065,3472.740000000003
2021-08-19,,,3472.740000000003
2021-08-20,BA,8.159999999999854,3480.900000000003
2021-08-21,,,3480.900000000003
2021-08-22,,,3480.900000000003
2021-08-23,,,3480.900000000003
2021-08-24,VZ,-25.42000000000023,3455.4800000000027
2021-08-25,,,3455.4800000000027
2021-08-26,AMGN,17.849999999999966,3473.3300000000027
2021-08-27,,,3473.3300000000027
2021-08-28,,,3473.3300000000027
2021-08-29,HON,11.550000000000152,3484.880000000003
2021-08-30,,,3484.880000000003
2021-08-31,,,3484.880000000003
2021-09-01,,,3484.880000000003
2021-09-02,BA,40.65000000000012,3525.530000000003
2021-09-03,,,3525.530000000003
2021-09-04,WBA,0.0,3525.530000000003
2021-09-05,,,3525.530000000003
2021-09-06,,,3525.530000000003
2021-09-07,,,3525.530000000003
2021-09-08,MMM,41.57999999999953,3567.1100000000024
2021-09-09,,,3567.1100000000024
2021-09-10,AMGN,40.79999999999973,3607.910000000002
2021-09-11,,,3607.910000000002
2021-09-12,,,3607.910000000002
2021-09-13,,,3607.910000000002
2021-09-14,,,3607.910000000002
2021-09-15,,,3607.910000000002
2021-09-16,,,3607.910000000002
2021-09-17,BA,0.0,3607.910000000002
2021-09-18,,,3607.910000000002
2021-09-19,,,3607.910000000002
2021-09-20,,,3607.910000000002
2021-09-21,AMGN,-23.52000000000044,3584.3900000000017
2021-09-22,,,3584.3900000000017
2021-09-23,,,3584.3900000000017
2021-09-24,UNH,-7.599999999999909,3576.790000000002
2021-09-25,,,3576.790000000002
2021-09-26,KO,-57.41999999999983,3519.370000000002
2021-09-27,,,3519.370000000002
2021-09-28,,,3519.370000000002
2021-09-29,,,3519.370000000002
2021-09-30,,,3519.370000000002
2021-10-01,,,3519.370000000002
2021-10-02,,,3519.370000000002
2021-10-03,MRK,73.09999999999951,3592.4700000000016
2021-10-04,,,3592.4700000000016
2021-10-05,,,3592.4700000000016
2021-10-06,V,35.67999999999984,3628.1500000000015
2021-10-07,,,3628.1500000000015
2021-10-08,MMM,-17.000000000000455,3611.150000000001
2021-10-09,,,3611.150000000001
2021-10-10,VZ,-64.98999999999992,3546.160000000001
2021-10-11,,,3546.160000000001
2021-10-12,,,3546.160000000001
2021-10-13,,,3546.160000000001
2021-10-14,,,3546.160000000001
2021-10-15,,,3546.160000000001
2021-10-16,,,3546.160000000001
2021-10-17,,,3546.160000000001
2021-10-18,,,3546.160000000001
2021-10-19,MRK,105.29999999999951,3651.460000000001
2021-10-20,,,3651.460000000001
2021-10-21,V,-17.699999999999676,3633.760000000001
2021-10-22,,,3633.760000000001
2021-10-23,BA,-1.6999999999999034,3632.0600000000013
2021-10-24,,,3632.0600000000013
2021-10-25,,,3632.0600000000013
2021-10-26,,,3632.0600000000013
2021-10-27,MCD,212.4000000000004,3844.460000000002
2021-10-28,,,3844.460000000002
2021-10-29,,,3844.460000000002
2021-10-30,,,3844.460000000002
2021-10-31,,,3844.460000000002
2021-11-01,,,3844.460000000002
2021-11-02,,,3844.460000000002
2021-11-03,TRV,34.320000000000164,3878.780000000002
2021-11-04,,,3878.780000000002
2021-11-05,V,142.01999999999975,4020.800000000002
2021-11-06,,,4020.800000000002
2021-11-07,GS,-15.569999999999652,4005.2300000000023
2021-11-08,,,4005.2300000000023
2021-11-09,,,4005.2300000000023
2021-11-10,,,4005.2300000000023
2021-11-11,AAPL,150.39000000000058,4155.620000000003
2021-11-12,,,4155.620000000003
2021-11-13,,,4155.620000000003
2021-11-14,,,4155.620000000003
2021-11-15,,,4155.620000000003
2021-11-16,,,4155.620000000003
2021-11-17,,,4155.620000000003
2021-11-18,,,4155.620000000003
2021-11-19,TRV,-91.0,4064.6200000000026
2021-11-20,,,4064.6200000000026
2021-11-21,TRV,112.84000000000007,4177.460000000003
2021-11-22,,,4177.460000000003
2021-11-23,,,4177.460000000003
2021-11-24,DIS,-78.83999999999966,4098.6200000000035
2021-11-25,,,4098.6200000000035
2021-11-26,,,4098.6200000000035
2021-11-27,,,4098.6200000000035
2021-11-28,AMGN,1.5999999999996817,4100.220000000003
2021-11-29,,,4100.220000000003
2021-11-30,,,4100.220000000003
2021-12-01,,,4100.220000000003
2021-12-02,,,4100.220000000003
2021-12-03,,,4100.220000000003
2021-12-04,CRM,6.450000000000102,4106.670000000003
2021-12-05,,,4106.670000000003
2021-12-06,,,4106.670000000003
2021-12-07,,,4106.670000000003
2021-12-08,INTC,-63.96000000000002,4042.7100000000028
2021-12-09,,,4042.7100000000028
2021-12-10,NKE,23.04000000000019,4065.7500000000027
2021-12-11,,,4065.7500000000027
2021-12-12,CRM,-196.4999999999995,3869.250000000003
2021-12-13,,,3869.250000000003
2021-12-14,,,3869.250000000003
2021-12-15,,,3869.250000000003
2021-12-16,,,3869.250000000003
2021-12-17,,,3869.250000000003
2021-12-18,,,3869.250000000003
2021-12-19,,,3869.250000000003
2021-12-20,HD,22.41000000000008,3891.660000000003
2021-12-21,,,3891.660000000003
2021-12-22,,,3891.660000000003
2021-12-23,TRV,-0.999999999999801,3890.660000000003
2021-12-24,,,3890.660000000003
2021-12-25,,,3890.660000000003
2021-12-26,,,3890.660000000003
2021-12-27,JPM,21.600000000000136,3912.260000000003
2021-12-28,,,3912.260000000003
2021-12-29,,,3912.260000000003
2021-12-30,,,3912.260000000003
2021-12-31,,,3912.260000000003


================================================
FILE: results/LR_v1_predict_0.95_21/history_df.csv
================================================
stock,buy_price,n_shares,sell_price,net_gain,buy_date,sell_date
BA,202.72,14,211.45,122.21999999999986,2021-01-05,2021-01-21
HON,205.23,15,202.25,-44.69999999999985,2021-01-22,2021-01-23
PG,130.0,23,128.38,-37.260000000000105,2021-01-24,2021-01-28
V,198.22,15,193.25,-74.54999999999998,2021-01-29,2021-01-30
GS,271.17,10,293.5,223.29999999999984,2021-01-31,2021-02-06
UNH,324.51,9,332.22,69.39000000000033,2021-02-07,2021-02-28
AAPL,121.26,26,127.79,169.78000000000003,2021-03-01,2021-03-02
CRM,213.47,16,206.0,-119.51999999999998,2021-03-03,2021-03-04
CRM,211.53,15,209.48,-30.75000000000017,2021-03-10,2021-03-19
V,206.9,15,216.86,149.40000000000012,2021-03-20,2021-04-02
GS,323.54,10,338.55,150.0999999999999,2021-04-06,2021-04-16
WBA,53.3,67,52.58,-48.239999999999924,2021-04-17,2021-04-23
PG,131.26,26,137.67,166.6599999999999,2021-04-27,2021-05-11
BA,220.78,16,234.82,224.63999999999987,2021-05-13,2021-05-22
V,226.77,17,234.96,139.22999999999996,2021-05-23,2021-06-13
CAT,220.7,18,219.01,-30.41999999999996,2021-06-14,2021-06-15
JNJ,164.49,24,161.98,-60.240000000000464,2021-06-16,2021-06-19
GS,348.83,11,368.75,219.12000000000018,2021-06-20,2021-06-25
MCD,232.42,18,230.37,-36.89999999999969,2021-06-26,2021-06-30
V,233.82,17,245.99,206.89000000000027,2021-07-01,2021-07-15
BA,217.74,20,206.99,-215.0,2021-07-17,2021-07-20
VZ,55.58,74,55.37,-15.540000000000063,2021-07-21,2021-08-05
VZ,55.22,74,55.01,-15.540000000000063,2021-08-07,2021-08-25
AMGN,221.59,18,220.87,-12.95999999999998,2021-08-26,2021-09-09
AMGN,215.58,19,213.75,-34.77000000000024,2021-09-10,2021-09-11
MMM,184.55,22,182.42,-46.860000000000525,2021-09-12,2021-09-15
BA,213.36,18,209.5,-69.48000000000025,2021-09-17,2021-09-21
GS,375.84,10,391.86,160.2000000000004,2021-09-22,2021-09-24
KO,53.89,76,53.61,-21.280000000000086,2021-09-26,2021-09-28
NKE,145.3,28,151.85,183.39999999999952,2021-09-29,2021-10-08
VZ,53.24,80,52.18,-84.80000000000018,2021-10-09,2021-10-12
KO,54.23,77,53.94,-22.329999999999934,2021-10-13,2021-10-19
IBM,122.57619612,33,122.14637232,-14.184185400000274,2021-10-22,2021-10-23
BA,212.97,19,207.03,-112.85999999999996,2021-10-24,2021-11-01
TRV,158.82,25,156.5,-57.99999999999983,2021-11-03,2021-11-05
AAPL,147.92,26,157.87,258.70000000000044,2021-11-11,2021-11-19
TRV,152.53,27,160.26,208.70999999999972,2021-11-20,2021-11-24
MMM,177.63,25,175.52,-52.74999999999963,2021-11-25,2021-11-28
AMGN,201.09,21,198.88,-46.41000000000017,2021-11-29,2021-12-01
GS,376.48,11,400.11,259.92999999999995,2021-12-02,2021-12-08
NKE,168.1,27,165.4,-72.8999999999997,2021-12-10,2021-12-15
CRM,253.12,17,247.21,-100.46999999999994,2021-12-17,2021-12-21


================================================
FILE: results/LR_v1_predict_0.95_21/running_gains_df.csv
================================================
Date,Stock,Gain,Total
2020-12-31,,,3000
2021-01-01,,,3000
2021-01-02,,,3000
2021-01-03,,,3000
2021-01-04,,,3000
2021-01-05,BA,122.21999999999986,3122.22
2021-01-06,,,3122.22
2021-01-07,,,3122.22
2021-01-08,,,3122.22
2021-01-09,,,3122.22
2021-01-10,,,3122.22
2021-01-11,,,3122.22
2021-01-12,,,3122.22
2021-01-13,,,3122.22
2021-01-14,,,3122.22
2021-01-15,,,3122.22
2021-01-16,,,3122.22
2021-01-17,,,3122.22
2021-01-18,,,3122.22
2021-01-19,,,3122.22
2021-01-20,,,3122.22
2021-01-21,,,3122.22
2021-01-22,HON,-44.69999999999985,3077.52
2021-01-23,,,3077.52
2021-01-24,PG,-37.260000000000105,3040.2599999999998
2021-01-25,,,3040.2599999999998
2021-01-26,,,3040.2599999999998
2021-01-27,,,3040.2599999999998
2021-01-28,,,3040.2599999999998
2021-01-29,V,-74.54999999999998,2965.7099999999996
2021-01-30,,,2965.7099999999996
2021-01-31,GS,223.29999999999984,3189.0099999999993
2021-02-01,,,3189.0099999999993
2021-02-02,,,3189.0099999999993
2021-02-03,,,3189.0099999999993
2021-02-04,,,3189.0099999999993
2021-02-05,,,3189.0099999999993
2021-02-06,,,3189.0099999999993
2021-02-07,UNH,69.39000000000033,3258.3999999999996
2021-02-08,,,3258.3999999999996
2021-02-09,,,3258.3999999999996
2021-02-10,,,3258.3999999999996
2021-02-11,,,3258.3999999999996
2021-02-12,,,3258.3999999999996
2021-02-13,,,3258.3999999999996
2021-02-14,,,3258.3999999999996
2021-02-15,,,3258.3999999999996
2021-02-16,,,3258.3999999999996
2021-02-17,,,3258.3999999999996
2021-02-18,,,3258.3999999999996
2021-02-19,,,3258.3999999999996
2021-02-20,,,3258.3999999999996
2021-02-21,,,3258.3999999999996
2021-02-22,,,3258.3999999999996
2021-02-23,,,3258.3999999999996
2021-02-24,,,3258.3999999999996
2021-02-25,,,3258.3999999999996
2021-02-26,,,3258.3999999999996
2021-02-27,,,3258.3999999999996
2021-02-28,,,3258.3999999999996
2021-03-01,AAPL,169.78000000000003,3428.18
2021-03-02,,,3428.18
2021-03-03,CRM,-119.51999999999998,3308.66
2021-03-04,,,3308.66
2021-03-05,,,3308.66
2021-03-06,,,3308.66
2021-03-07,,,3308.66
2021-03-08,,,3308.66
2021-03-09,,,3308.66
2021-03-10,CRM,-30.75000000000017,3277.91
2021-03-11,,,3277.91
2021-03-12,,,3277.91
2021-03-13,,,3277.91
2021-03-14,,,3277.91
2021-03-15,,,3277.91
2021-03-16,,,3277.91
2021-03-17,,,3277.91
2021-03-18,,,3277.91
2021-03-19,,,3277.91
2021-03-20,V,149.40000000000012,3427.31
2021-03-21,,,3427.31
2021-03-22,,,3427.31
2021-03-23,,,3427.31
2021-03-24,,,3427.31
2021-03-25,,,3427.31
2021-03-26,,,3427.31
2021-03-27,,,3427.31
2021-03-28,,,3427.31
2021-03-29,,,3427.31
2021-03-30,,,3427.31
2021-03-31,,,3427.31
2021-04-01,,,3427.31
2021-04-02,,,3427.31
2021-04-03,,,3427.31
2021-04-04,,,3427.31
2021-04-05,,,3427.31
2021-04-06,GS,150.0999999999999,3577.41
2021-04-07,,,3577.41
2021-04-08,,,3577.41
2021-04-09,,,3577.41
2021-04-10,,,3577.41
2021-04-11,,,3577.41
2021-04-12,,,3577.41
2021-04-13,,,3577.41
2021-04-14,,,3577.41
2021-04-15,,,3577.41
2021-04-16,,,3577.41
2021-04-17,WBA,-48.23999999999992,3529.17
2021-04-18,,,3529.17
2021-04-19,,,3529.17
2021-04-20,,,3529.17
2021-04-21,,,3529.17
2021-04-22,,,3529.17
2021-04-23,,,3529.17
2021-04-24,,,3529.17
2021-04-25,,,3529.17
2021-04-26,,,3529.17
2021-04-27,PG,166.6599999999999,3695.83
2021-04-28,,,3695.83
2021-04-29,,,3695.83
2021-04-30,,,3695.83
2021-05-01,,,3695.83
2021-05-02,,,3695.83
2021-05-03,,,3695.83
2021-05-04,,,3695.83
2021-05-05,,,3695.83
2021-05-06,,,3695.83
2021-05-07,,,3695.83
2021-05-08,,,3695.83
2021-05-09,,,3695.83
2021-05-10,,,3695.83
2021-05-11,,,3695.83
2021-05-12,,,3695.83
2021-05-13,BA,224.63999999999987,3920.47
2021-05-14,,,3920.47
2021-05-15,,,3920.47
2021-05-16,,,3920.47
2021-05-17,,,3920.47
2021-05-18,,,3920.47
2021-05-19,,,3920.47
2021-05-20,,,3920.47
2021-05-21,,,3920.47
2021-05-22,,,3920.47
2021-05-23,V,139.22999999999996,4059.7
2021-05-24,,,4059.7
2021-05-25,,,4059.7
2021-05-26,,,4059.7
2021-05-27,,,4059.7
2021-05-28,,,4059.7
2021-05-29,,,4059.7
2021-05-30,,,4059.7
2021-05-31,,,4059.7
2021-06-01,,,4059.7
2021-06-02,,,4059.7
2021-06-03,,,4059.7
2021-06-04,,,4059.7
2021-06-05,,,4059.7
2021-06-06,,,4059.7
2021-06-07,,,4059.7
2021-06-08,,,4059.7
2021-06-09,,,4059.7
2021-06-10,,,4059.7
2021-06-11,,,4059.7
2021-06-12,,,4059.7
2021-06-13,,,4059.7
2021-06-14,CAT,-30.41999999999996,4029.2799999999997
2021-06-15,,,4029.2799999999997
2021-06-16,JNJ,-60.240000000000464,3969.039999999999
2021-06-17,,,3969.039999999999
2021-06-18,,,3969.039999999999
2021-06-19,,,3969.039999999999
2021-06-20,GS,219.12000000000015,4188.159999999999
2021-06-21,,,4188.159999999999
2021-06-22,,,4188.159999999999
2021-06-23,,,4188.159999999999
2021-06-24,,,4188.159999999999
2021-06-25,,,4188.159999999999
2021-06-26,MCD,-36.89999999999969,4151.259999999999
2021-06-27,,,4151.259999999999
2021-06-28,,,4151.259999999999
2021-06-29,,,4151.259999999999
2021-06-30,,,4151.259999999999
2021-07-01,V,206.89000000000027,4358.15
2021-07-02,,,4358.15
2021-07-03,,,4358.15
2021-07-04,,,4358.15
2021-07-05,,,4358.15
2021-07-06,,,4358.15
2021-07-07,,,4358.15
2021-07-08,,,4358.15
2021-07-09,,,4358.15
2021-07-10,,,4358.15
2021-07-11,,,4358.15
2021-07-12,,,4358.15
2021-07-13,,,4358.15
2021-07-14,,,4358.15
2021-07-15,,,4358.15
2021-07-16,,,4358.15
2021-07-17,BA,-215.0,4143.15
2021-07-18,,,4143.15
2021-07-19,,,4143.15
2021-07-20,,,4143.15
2021-07-21,VZ,-15.540000000000065,4127.61
2021-07-22,,,4127.61
2021-07-23,,,4127.61
2021-07-24,,,4127.61
2021-07-25,,,4127.61
2021-07-26,,,4127.61
2021-07-27,,,4127.61
2021-07-28,,,4127.61
2021-07-29,,,4127.61
2021-07-30,,,4127.61
2021-07-31,,,4127.61
2021-08-01,,,4127.61
2021-08-02,,,4127.61
2021-08-03,,,4127.61
2021-08-04,,,4127.61
2021-08-05,,,4127.61
2021-08-06,,,4127.61
2021-08-07,VZ,-15.540000000000065,4112.07
2021-08-08,,,4112.07
2021-08-09,,,4112.07
2021-08-10,,,4112.07
2021-08-11,,,4112.07
2021-08-12,,,4112.07
2021-08-13,,,4112.07
2021-08-14,,,4112.07
2021-08-15,,,4112.07
2021-08-16,,,4112.07
2021-08-17,,,4112.07
2021-08-18,,,4112.07
2021-08-19,,,4112.07
2021-08-20,,,4112.07
2021-08-21,,,4112.07
2021-08-22,,,4112.07
2021-08-23,,,4112.07
2021-08-24,,,4112.07
2021-08-25,,,4112.07
2021-08-26,AMGN,-12.95999999999998,4099.11
2021-08-27,,,4099.11
2021-08-28,,,4099.11
2021-08-29,,,4099.11
2021-08-30,,,4099.11
2021-08-31,,,4099.11
2021-09-01,,,4099.11
2021-09-02,,,4099.11
2021-09-03,,,4099.11
2021-09-04,,,4099.11
2021-09-05,,,4099.11
2021-09-06,,,4099.11
2021-09-07,,,4099.11
2021-09-08,,,4099.11
2021-09-09,,,4099.11
2021-09-10,AMGN,-34.77000000000024,4064.3399999999992
2021-09-11,,,4064.3399999999992
2021-09-12,MMM,-46.860000000000525,4017.4799999999987
2021-09-13,,,4017.4799999999987
2021-09-14,,,4017.4799999999987
2021-09-15,,,4017.4799999999987
2021-09-16,,,4017.4799999999987
2021-09-17,BA,-69.48000000000025,3947.999999999998
2021-09-18,,,3947.999999999998
2021-09-19,,,3947.999999999998
2021-09-20,,,3947.999999999998
2021-09-21,,,3947.999999999998
2021-09-22,GS,160.2000000000004,4108.199999999999
2021-09-23,,,4108.199999999999
2021-09-24,,,4108.199999999999
2021-09-25,,,4108.199999999999
2021-09-26,KO,-21.280000000000086,4086.9199999999987
2021-09-27,,,4086.9199999999987
2021-09-28,,,4086.9199999999987
2021-09-29,NKE,183.39999999999952,4270.319999999998
2021-09-30,,,4270.319999999998
2021-10-01,,,4270.319999999998
2021-10-02,,,4270.319999999998
2021-10-03,,,4270.319999999998
2021-10-04,,,4270.319999999998
2021-10-05,,,4270.319999999998
2021-10-06,,,4270.319999999998
2021-10-07,,,4270.319999999998
2021-10-08,,,4270.319999999998
2021-10-09,VZ,-84.80000000000018,4185.519999999998
2021-10-10,,,4185.519999999998
2021-10-11,,,4185.519999999998
2021-10-12,,,4185.519999999998
2021-10-13,KO,-22.32999999999993,4163.189999999998
2021-10-14,,,4163.189999999998
2021-10-15,,,4163.189999999998
2021-10-16,,,4163.189999999998
2021-10-17,,,4163.189999999998
2021-10-18,,,4163.189999999998
2021-10-19,,,4163.189999999998
2021-10-20,,,4163.189999999998
2021-10-21,,,4163.189999999998
2021-10-22,IBM,-14.184185400000274,4149.005814599997
2021-10-23,,,4149.005814599997
2021-10-24,BA,-112.85999999999996,4036.1458145999973
2021-10-25,,,4036.1458145999973
2021-10-26,,,4036.1458145999973
2021-10-27,,,4036.1458145999973
2021-10-28,,,4036.1458145999973
2021-10-29,,,4036.1458145999973
2021-10-30,,,4036.1458145999973
2021-10-31,,,4036.1458145999973
2021-11-01,,,4036.1458145999973
2021-11-02,,,4036.1458145999973
2021-11-03,TRV,-57.99999999999983,3978.1458145999973
2021-11-04,,,3978.1458145999973
2021-11-05,,,3978.1458145999973
2021-11-06,,,3978.1458145999973
2021-11-07,,,3978.1458145999973
2021-11-08,,,3978.1458145999973
2021-11-09,,,3978.1458145999973
2021-11-10,,,3978.1458145999973
2021-11-11,AAPL,258.70000000000044,4236.8458145999975
2021-11-12,,,4236.8458145999975
2021-11-13,,,4236.8458145999975
2021-11-14,,,4236.8458145999975
2021-11-15,,,4236.8458145999975
2021-11-16,,,4236.8458145999975
2021-11-17,,,4236.8458145999975
2021-11-18,,,4236.8458145999975
2021-11-19,,,4236.8458145999975
2021-11-20,TRV,208.70999999999967,4445.555814599998
2021-11-21,,,4445.555814599998
2021-11-22,,,4445.555814599998
2021-11-23,,,4445.555814599998
2021-11-24,,,4445.555814599998
2021-11-25,MMM,-52.74999999999963,4392.805814599998
2021-11-26,,,4392.805814599998
2021-11-27,,,4392.805814599998
2021-11-28,,,4392.805814599998
2021-11-29,AMGN,-46.41000000000017,4346.395814599998
2021-11-30,,,4346.395814599998
2021-12-01,,,4346.395814599998
2021-12-02,GS,259.92999999999995,4606.325814599998
2021-12-03,,,4606.325814599998
2021-12-04,,,4606.325814599998
2021-12-05,,,4606.325814599998
2021-12-06,,,4606.325814599998
2021-12-07,,,4606.325814599998
2021-12-08,,,4606.325814599998
2021-12-09,,,4606.325814599998
2021-12-10,NKE,-72.8999999999997,4533.425814599998
2021-12-11,,,4533.425814599998
2021-12-12,,,4533.425814599998
2021-12-13,,,4533.425814599998
2021-12-14,,,4533.425814599998
2021-12-15,,,4533.425814599998
2021-12-16,,,4533.425814599998
2021-12-17,CRM,-100.46999999999994,4432.955814599998
2021-12-18,,,4432.955814599998
2021-12-19,,,4432.955814599998
2021-12-20,,,4432.955814599998
2021-12-21,,,4432.955814599998
2021-12-22,,,4432.955814599998
2021-12-23,,,4432.955814599998
2021-12-24,,,4432.955814599998
2021-12-25,,,4432.955814599998
2021-12-26,,,4432.955814599998
2021-12-27,,,4432.955814599998
2021-12-28,,,4432.955814599998
2021-12-29,,,4432.955814599998
2021-12-30,,,4432.955814599998
2021-12-31,,,4432.955814599998


================================================
FILE: results/LR_v1_predict_0.9_10/history_df.csv
================================================
stock,buy_price,n_shares,sell_price,net_gain,buy_date,sell_date
BA,202.72,14,211.63,124.73999999999995,2021-01-05,2021-01-06
MSFT,212.25,14,219.62,103.18000000000006,2021-01-07,2021-01-09
MMM,165.2,19,170.22,95.3800000000002,2021-01-12,2021-01-21
HON,205.23,16,195.37,-157.75999999999976,2021-01-22,2021-01-30
V,193.25,16,202.61,149.76000000000022,2021-01-31,2021-02-03
MRK,77.32,42,74.89,-102.05999999999969,2021-02-04,2021-02-11
PG,128.33,25,127.12,-30.2500000000002,2021-02-12,2021-02-22
AAPL,126.0,25,120.99,-125.25000000000013,2021-02-23,2021-02-26
AAPL,121.26,25,127.79,163.25000000000003,2021-02-27,2021-03-02
CRM,213.47,15,206.0,-112.04999999999998,2021-03-03,2021-03-04
AMGN,221.91,14,228.99,99.12000000000018,2021-03-05,2021-03-10
INTC,62.25,51,64.78,129.03000000000006,2021-03-11,2021-03-17
PG,128.42,25,132.6,104.50000000000017,2021-03-18,2021-03-24
GS,328.65,10,327.64,-10.099999999999909,2021-03-25,2021-04-04
KO,52.51,65,53.08,37.05000000000002,2021-04-05,2021-04-15
JNJ,160.39,21,166.48,127.89000000000007,2021-04-16,2021-04-21
VZ,58.14,61,56.32,-111.02000000000001,2021-04-22,2021-04-28
WMT,137.89,25,142.12,105.75000000000045,2021-04-29,2021-05-04
CRM,215.4,16,217.66,36.159999999999854,2021-05-06,2021-05-16
VZ,58.69,61,56.92,-107.96999999999976,2021-05-17,2021-05-20
VZ,56.79,61,56.49,-18.299999999999827,2021-05-21,2021-05-31
HD,318.91,10,307.34,-115.7000000000005,2021-06-01,2021-06-10
CAT,225.73,14,217.16,-119.9799999999999,2021-06-11,2021-06-17
CAT,209.45,15,219.34,148.35000000000022,2021-06-18,2021-06-25
MCD,232.42,14,233.63,16.94000000000011,2021-06-26,2021-07-06
BA,231.78,14,239.59,109.34000000000003,2021-07-08,2021-07-10
MRK,77.99,45,76.17,-81.8999999999997,2021-07-11,2021-07-21
VZ,55.95,61,55.78,-10.370000000000104,2021-07-22,2021-08-01
VZ,55.78,61,55.57,-12.810000000000052,2021-08-02,2021-08-12
V,231.79,14,231.36,-6.019999999999698,2021-08-13,2021-08-23
VZ,55.42,61,55.29,-7.930000000000156,2021-08-24,2021-09-03
WBA,51.29,66,49.45,-121.43999999999976,2021-09-04,2021-09-11
MMM,184.55,17,178.42,-104.2100000000004,2021-09-12,2021-09-22
CAT,191.35,16,200.0,138.4000000000001,2021-09-23,2021-09-28
NKE,145.3,22,151.85,144.09999999999962,2021-09-29,2021-10-08
VZ,53.24,65,51.33,-124.15000000000023,2021-10-09,2021-10-13
JPM,161.0,20,166.61,112.20000000000027,2021-10-14,2021-10-16
TRV,155.64,22,162.37,148.0600000000004,2021-10-17,2021-10-23
BA,212.97,16,212.77,-3.199999999999818,2021-10-24,2021-11-03
V,208.78,17,216.67,134.12999999999977,2021-11-05,2021-11-06
GS,407.08,9,403.09,-35.91000000000008,2021-11-07,2021-11-17
GS,391.55,9,406.34,133.10999999999967,2021-11-18,2021-11-24
MMM,177.63,21,170.04,-159.39000000000007,2021-11-25,2021-12-01
GS,376.48,9,389.3,115.37999999999994,2021-12-02,2021-12-07
INTC,52.57,72,50.48,-150.48000000000025,2021-12-08,2021-12-10
CRM,266.03,13,255.59,-135.7199999999996,2021-12-11,2021-12-15
VZ,50.55,69,52.75,151.80000000000018,2021-12-16,2021-12-17
HD,387.98,9,404.09,144.9899999999996,2021-12-18,2021-12-28


================================================
FILE: results/LR_v1_predict_0.9_10/running_gains_df.csv
================================================
Date,Stock,Gain,Total
2020-12-31,,,3000
2021-01-01,,,3000
2021-01-02,,,3000
2021-01-03,,,3000
2021-01-04,,,3000
2021-01-05,BA,124.73999999999997,3124.74
2021-01-06,,,3124.74
2021-01-07,MSFT,103.18000000000006,3227.92
2021-01-08,,,3227.92
2021-01-09,,,3227.92
2021-01-10,,,3227.92
2021-01-11,,,3227.92
2021-01-12,MMM,95.3800000000002,3323.3
2021-01-13,,,3323.3
2021-01-14,,,3323.3
2021-01-15,,,3323.3
2021-01-16,,,3323.3
2021-01-17,,,3323.3
2021-01-18,,,3323.3
2021-01-19,,,3323.3
2021-01-20,,,3323.3
2021-01-21,,,3323.3
2021-01-22,HON,-157.75999999999976,3165.5400000000004
2021-01-23,,,3165.5400000000004
2021-01-24,,,3165.5400000000004
2021-01-25,,,3165.5400000000004
2021-01-26,,,3165.5400000000004
2021-01-27,,,3165.5400000000004
2021-01-28,,,3165.5400000000004
2021-01-29,,,3165.5400000000004
2021-01-30,,,3165.5400000000004
2021-01-31,V,149.76000000000022,3315.3000000000006
2021-02-01,,,3315.3000000000006
2021-02-02,,,3315.3000000000006
2021-02-03,,,3315.3000000000006
2021-02-04,MRK,-102.05999999999968,3213.240000000001
2021-02-05,,,3213.240000000001
2021-02-06,,,3213.240000000001
2021-02-07,,,3213.240000000001
2021-02-08,,,3213.240000000001
2021-02-09,,,3213.240000000001
2021-02-10,,,3213.240000000001
2021-02-11,,,3213.240000000001
2021-02-12,PG,-30.2500000000002,3182.990000000001
2021-02-13,,,3182.990000000001
2021-02-14,,,3182.990000000001
2021-02-15,,,3182.990000000001
2021-02-16,,,3182.990000000001
2021-02-17,,,3182.990000000001
2021-02-18,,,3182.990000000001
2021-02-19,,,3182.990000000001
2021-02-20,,,3182.990000000001
2021-02-21,,,3182.990000000001
2021-02-22,,,3182.990000000001
2021-02-23,AAPL,-125.25000000000011,3057.740000000001
2021-02-24,,,3057.740000000001
2021-02-25,,,3057.740000000001
2021-02-26,,,3057.740000000001
2021-02-27,AAPL,163.25000000000003,3220.990000000001
2021-02-28,,,3220.990000000001
2021-03-01,,,3220.990000000001
2021-03-02,,,3220.990000000001
2021-03-03,CRM,-112.04999999999998,3108.940000000001
2021-03-04,,,3108.940000000001
2021-03-05,AMGN,99.12000000000018,3208.0600000000013
2021-03-06,,,3208.0600000000013
2021-03-07,,,3208.0600000000013
2021-03-08,,,3208.0600000000013
2021-03-09,,,3208.0600000000013
2021-03-10,,,3208.0600000000013
2021-03-11,INTC,129.03000000000006,3337.0900000000015
2021-03-12,,,3337.0900000000015
2021-03-13,,,3337.0900000000015
2021-03-14,,,3337.0900000000015
2021-03-15,,,3337.0900000000015
2021-03-16,,,3337.0900000000015
2021-03-17,,,3337.0900000000015
2021-03-18,PG,104.50000000000016,3441.5900000000015
2021-03-19,,,3441.5900000000015
2021-03-20,,,3441.5900000000015
2021-03-21,,,3441.5900000000015
2021-03-22,,,3441.5900000000015
2021-03-23,,,3441.5900000000015
2021-03-24,,,3441.5900000000015
2021-03-25,GS,-10.099999999999907,3431.4900000000016
2021-03-26,,,3431.4900000000016
2021-03-27,,,3431.4900000000016
2021-03-28,,,3431.4900000000016
2021-03-29,,,3431.4900000000016
2021-03-30,,,3431.4900000000016
2021-03-31,,,3431.4900000000016
2021-04-01,,,3431.4900000000016
2021-04-02,,,3431.4900000000016
2021-04-03,,,3431.4900000000016
2021-04-04,,,3431.4900000000016
2021-04-05,KO,37.05000000000002,3468.540000000002
2021-04-06,,,3468.540000000002
2021-04-07,,,3468.540000000002
2021-04-08,,,3468.540000000002
2021-04-09,,,3468.540000000002
2021-04-10,,,3468.540000000002
2021-04-11,,,3468.540000000002
2021-04-12,,,3468.540000000002
2021-04-13,,,3468.540000000002
2021-04-14,,,3468.540000000002
2021-04-15,,,3468.540000000002
2021-04-16,JNJ,127.89000000000009,3596.4300000000017
2021-04-17,,,3596.4300000000017
2021-04-18,,,3596.4300000000017
2021-04-19,,,3596.4300000000017
2021-04-20,,,3596.4300000000017
2021-04-21,,,3596.4300000000017
2021-04-22,VZ,-111.02,3485.4100000000017
2021-04-23,,,3485.4100000000017
2021-04-24,,,3485.4100000000017
2021-04-25,,,3485.4100000000017
2021-04-26,,,3485.4100000000017
2021-04-27,,,3485.4100000000017
2021-04-28,,,3485.4100000000017
2021-04-29,WMT,105.75000000000044,3591.160000000002
2021-04-30,,,3591.160000000002
2021-05-01,,,3591.160000000002
2021-05-02,,,3591.160000000002
2021-05-03,,,3591.160000000002
2021-05-04,,,3591.160000000002
2021-05-05,,,3591.160000000002
2021-05-06,CRM,36.159999999999854,3627.320000000002
2021-05-07,,,3627.320000000002
2021-05-08,,,3627.320000000002
2021-05-09,,,3627.320000000002
2021-05-10,,,3627.320000000002
2021-05-11,,,3627.320000000002
2021-05-12,,,3627.320000000002
2021-05-13,,,3627.320000000002
2021-05-14,,,3627.320000000002
2021-05-15,,,3627.320000000002
2021-05-16,,,3627.320000000002
2021-05-17,VZ,-107.96999999999976,3519.350000000002
2021-05-18,,,3519.350000000002
2021-05-19,,,3519.350000000002
2021-05-20,,,3519.350000000002
2021-05-21,VZ,-18.299999999999827,3501.0500000000025
2021-05-22,,,3501.0500000000025
2021-05-23,,,3501.0500000000025
2021-05-24,,,3501.0500000000025
2021-05-25,,,3501.0500000000025
2021-05-26,,,3501.0500000000025
2021-05-27,,,3501.0500000000025
2021-05-28,,,3501.0500000000025
2021-05-29,,,3501.0500000000025
2021-05-30,,,3501.0500000000025
2021-05-31,,,3501.0500000000025
2021-06-01,HD,-115.7000000000005,3385.350000000002
2021-06-02,,,3385.350000000002
2021-06-03,,,3385.350000000002
2021-06-04,,,3385.350000000002
2021-06-05,,,3385.350000000002
2021-06-06,,,3385.350000000002
2021-06-07,,,3385.350000000002
2021-06-08,,,3385.350000000002
2021-06-09,,,3385.350000000002
2021-06-10,,,3385.350000000002
2021-06-11,CAT,-119.9799999999999,3265.370000000002
2021-06-12,,,3265.370000000002
2021-06-13,,,3265.370000000002
2021-06-14,,,3265.370000000002
2021-06-15,,,3265.370000000002
2021-06-16,,,3265.370000000002
2021-06-17,,,3265.370000000002
2021-06-18,CAT,148.35000000000022,3413.7200000000025
2021-06-19,,,3413.7200000000025
2021-06-20,,,3413.7200000000025
2021-06-21,,,3413.7200000000025
2021-06-22,,,3413.7200000000025
2021-06-23,,,3413.7200000000025
2021-06-24,,,3413.7200000000025
2021-06-25,,,3413.7200000000025
2021-06-26,MCD,16.94000000000011,3430.6600000000026
2021-06-27,,,3430.6600000000026
2021-06-28,,,3430.6600000000026
2021-06-29,,,3430.6600000000026
2021-06-30,,,3430.6600000000026
2021-07-01,,,3430.6600000000026
2021-07-02,,,3430.6600000000026
2021-07-03,,,3430.6600000000026
2021-07-04,,,3430.6600000000026
2021-07-05,,,3430.6600000000026
2021-07-06,,,3430.6600000000026
2021-07-07,,,3430.6600000000026
2021-07-08,BA,109.34000000000005,3540.0000000000027
2021-07-09,,,3540.0000000000027
2021-07-10,,,3540.0000000000027
2021-07-11,MRK,-81.8999999999997,3458.100000000003
2021-07-12,,,3458.100000000003
2021-07-13,,,3458.100000000003
2021-07-14,,,3458.100000000003
2021-07-15,,,3458.100000000003
2021-07-16,,,3458.100000000003
2021-07-17,,,3458.100000000003
2021-07-18,,,3458.100000000003
2021-07-19,,,3458.100000000003
2021-07-20,,,3458.100000000003
2021-07-21,,,3458.100000000003
2021-07-22,VZ,-10.370000000000104,3447.730000000003
2021-07-23,,,3447.730000000003
2021-07-24,,,3447.730000000003
2021-07-25,,,3447.730000000003
2021-07-26,,,3447.730000000003
2021-07-27,,,3447.730000000003
2021-07-28,,,3447.730000000003
2021-07-29,,,3447.730000000003
2021-07-30,,,3447.730000000003
2021-07-31,,,3447.730000000003
2021-08-01,,,3447.730000000003
2021-08-02,VZ,-12.810000000000052,3434.9200000000033
2021-08-03,,,3434.9200000000033
2021-08-04,,,3434.9200000000033
2021-08-05,,,3434.9200000000033
2021-08-06,,,3434.9200000000033
2021-08-07,,,3434.9200000000033
2021-08-08,,,3434.9200000000033
2021-08-09,,,3434.9200000000033
2021-08-10,,,3434.9200000000033
2021-08-11,,,3434.9200000000033
2021-08-12,,,3434.9200000000033
2021-08-13,V,-6.019999999999698,3428.9000000000037
2021-08-14,,,3428.9000000000037
2021-08-15,,,3428.9000000000037
2021-08-16,,,3428.9000000000037
2021-08-17,,,3428.9000000000037
2021-08-18,,,3428.9000000000037
2021-08-19,,,3428.9000000000037
2021-08-20,,,3428.9000000000037
2021-08-21,,,3428.9000000000037
2021-08-22,,,3428.9000000000037
2021-08-23,,,3428.9000000000037
2021-08-24,VZ,-7.930000000000156,3420.9700000000034
2021-08-25,,,3420.9700000000034
2021-08-26,,,3420.9700000000034
2021-08-27,,,3420.9700000000034
2021-08-28,,,3420.9700000000034
2021-08-29,,,3420.9700000000034
2021-08-30,,,3420.9700000000034
2021-08-31,,,3420.9700000000034
2021-09-01,,,3420.9700000000034
2021-09-02,,,3420.9700000000034
2021-09-03,,,3420.9700000000034
2021-09-04,WBA,-121.43999999999976,3299.530000000004
2021-09-05,,,3299.530000000004
2021-09-06,,,3299.530000000004
2021-09-07,,,3299.530000000004
2021-09-08,,,3299.530000000004
2021-09-09,,,3299.530000000004
2021-09-10,,,3299.530000000004
2021-09-11,,,3299.530000000004
2021-09-12,MMM,-104.2100000000004,3195.3200000000033
2021-09-13,,,3195.3200000000033
2021-09-14,,,3195.3200000000033
2021-09-15,,,3195.3200000000033
2021-09-16,,,3195.3200000000033
2021-09-17,,,3195.3200000000033
2021-09-18,,,3195.3200000000033
2021-09-19,,,3195.3200000000033
2021-09-20,,,3195.3200000000033
2021-09-21,,,3195.3200000000033
2021-09-22,,,3195.3200000000033
2021-09-23,CAT,138.4000000000001,3333.7200000000034
2021-09-24,,,3333.7200000000034
2021-09-25,,,3333.7200000000034
2021-09-26,,,3333.7200000000034
2021-09-27,,,3333.7200000000034
2021-09-28,,,3333.7200000000034
2021-09-29,NKE,144.09999999999962,3477.820000000003
2021-09-30,,,3477.820000000003
2021-10-01,,,3477.820000000003
2021-10-02,,,3477.820000000003
2021-10-03,,,3477.820000000003
2021-10-04,,,3477.820000000003
2021-10-05,,,3477.820000000003
2021-10-06,,,3477.820000000003
2021-10-07,,,3477.820000000003
2021-10-08,,,3477.820000000003
2021-10-09,VZ,-124.15000000000023,3353.670000000003
2021-10-10,,,3353.670000000003
2021-10-11,,,3353.670000000003
2021-10-12,,,3353.670000000003
2021-10-13,,,3353.670000000003
2021-10-14,JPM,112.20000000000029,3465.870000000003
2021-10-15,,,3465.870000000003
2021-10-16,,,3465.870000000003
2021-10-17,TRV,148.0600000000004,3613.9300000000035
2021-10-18,,,3613.9300000000035
2021-10-19,,,3613.9300000000035
2021-10-20,,,3613.9300000000035
2021-10-21,,,3613.9300000000035
2021-10-22,,,3613.9300000000035
2021-10-23,,,3613.9300000000035
2021-10-24,BA,-3.199999999999818,3610.7300000000037
2021-10-25,,,3610.7300000000037
2021-10-26,,,3610.7300000000037
2021-10-27,,,3610.7300000000037
2021-10-28,,,3610.7300000000037
2021-10-29,,,3610.7300000000037
2021-10-30,,,3610.7300000000037
2021-10-31,,,3610.7300000000037
2021-11-01,,,3610.7300000000037
2021-11-02,,,3610.7300000000037
2021-11-03,,,3610.7300000000037
2021-11-04,,,3610.7300000000037
2021-11-05,V,134.12999999999977,3744.8600000000033
2021-11-06,,,3744.8600000000033
2021-11-07,GS,-35.91000000000008,3708.9500000000035
2021-11-08,,,3708.9500000000035
2021-11-09,,,3708.9500000000035
2021-11-10,,,3708.9500000000035
2021-11-11,,,3708.9500000000035
2021-11-12,,,3708.9500000000035
2021-11-13,,,3708.9500000000035
2021-11-14,,,3708.9500000000035
2021-11-15,,,3708.9500000000035
2021-11-16,,,3708.9500000000035
2021-11-17,,,3708.9500000000035
2021-11-18,GS,133.10999999999967,3842.060000000003
2021-11-19,,,3842.060000000003
2021-11-20,,,3842.060000000003
2021-11-21,,,3842.060000000003
2021-11-22,,,3842.060000000003
2021-11-23,,,3842.060000000003
2021-11-24,,,3842.060000000003
2021-11-25,MMM,-159.39000000000007,3682.6700000000033
2021-11-26,,,3682.6700000000033
2021-11-27,,,3682.6700000000033
2021-11-28,,,3682.6700000000033
2021-11-29,,,3682.6700000000033
2021-11-30,,,3682.6700000000033
2021-12-01,,,3682.6700000000033
2021-12-02,GS,115.37999999999994,3798.0500000000034
2021-12-03,,,3798.0500000000034
2021-12-04,,,3798.0500000000034
2021-12-05,,,3798.0500000000034
2021-12-06,,,3798.0500000000034
2021-12-07,,,3798.0500000000034
2021-12-08,INTC,-150.48000000000025,3647.5700000000033
2021-12-09,,,3647.5700000000033
2021-12-10,,,3647.5700000000033
2021-12-11,CRM,-135.7199999999996,3511.8500000000035
2021-12-12,,,3511.8500000000035
2021-12-13,,,3511.8500000000035
2021-12-14,,,3511.8500000000035
2021-12-15,,,3511.8500000000035
2021-12-16,VZ,151.80000000000018,3663.6500000000037
2021-12-17,,,3663.6500000000037
2021-12-18,HD,144.9899999999996,3808.6400000000035
2021-12-19,,,3808.6400000000035
2021-12-20,,,3808.6400000000035
2021-12-21,,,3808.6400000000035
2021-12-22,,,3808.6400000000035
2021-12-23,,,3808.6400000000035
2021-12-24,,,3808.6400000000035
2021-12-25,,,3808.6400000000035
2021-12-26,,,3808.6400000000035
2021-12-27,,,3808.6400000000035
2021-12-28,,,3808.6400000000035
2021-12-29,,,3808.6400000000035
2021-12-30,,,3808.6400000000035
2021-12-31,,,3808.6400000000035


================================================
FILE: results/LR_v1_predict_1_1/history_df.csv
================================================
stock,buy_price,n_shares,sell_price,net_gain,buy_date,sell_date
WBA,39.88,75,39.88,0.0,2021-01-01,2021-01-02
VZ,58.75,51,58.53,-11.219999999999942,2021-01-03,2021-01-08
JPM,136.02,21,136.02,0.0,2021-01-09,2021-01-10
CRM,222.04,13,218.25,-49.2699999999999,2021-01-11,2021-01-12
CVX,93.34,31,93.25,-2.7900000000001057,2021-01-13,2021-01-14
WMT,146.97,19,144.64,-44.27000000000024,2021-01-15,2021-01-17
MSFT,212.65,13,224.97,160.1599999999999,2021-01-18,2021-01-22
HON,202.25,15,202.25,0.0,2021-01-23,2021-01-24
CRM,225.77,13,226.26,6.369999999999749,2021-01-25,2021-01-27
WMT,143.84,21,140.49,-70.34999999999988,2021-01-28,2021-01-31
GS,271.17,11,274.73,39.160000000000025,2021-02-01,2021-02-02
AXP,120.7,25,120.44,-6.500000000000128,2021-02-03,2021-02-04
AMGN,237.22,12,236.32,-10.800000000000068,2021-02-05,2021-02-06
NKE,145.11,20,145.11,0.0,2021-02-07,2021-02-08
UNH,324.34,9,329.63,47.610000000000184,2021-02-09,2021-02-10
CSCO,47.24,64,47.29,3.199999999999818,2021-02-11,2021-02-14
KO,50.69,60,50.69,0.0,2021-02-15,2021-02-16
VZ,54.15,56,56.99,159.0400000000002,2021-02-17,2021-02-18
KO,50.77,63,50.11,-41.58000000000023,2021-02-19,2021-02-20
CSCO,45.68,69,45.68,0.0,2021-02-21,2021-02-22
PG,126.58,25,127.66,26.999999999999957,2021-02-23,2021-02-25
INTC,60.4,53,60.78,20.140000000000136,2021-02-26,2021-02-28
CSCO,44.87,71,45.515,45.79500000000022,2021-03-01,2021-03-03
WBA,47.63,68,46.86,-52.36000000000021,2021-03-04,2021-03-05
BA,223.22,14,223.22,0.0,2021-03-06,2021-03-08
CVX,109.75,29,109.5,-7.25,2021-03-09,2021-03-10
UNH,349.6,9,353.1,31.5,2021-03-11,2021-03-12
DIS,197.16,16,197.16,0.0,2021-03-13,2021-03-14
PG,128.14,25,128.56,10.500000000000398,2021-03-15,2021-03-16
MCD,219.86,14,224.11,59.5,2021-03-17,2021-03-18
TRV,156.83,21,149.3,-158.13000000000002,2021-03-19,2021-03-22
MMM,189.47,16,188.33,-18.23999999999978,2021-03-23,2021-03-24
JNJ,161.91,19,164.93,57.380000000000194,2021-03-25,2021-03-27
MRK,77.39,41,77.39,0.0,2021-03-28,2021-03-29
WBA,52.85,60,55.58,163.7999999999998,2021-03-30,2021-04-08
CAT,230.48,14,230.75,3.7800000000001432,2021-04-09,2021-04-11
MSFT,255.85,13,259.5,47.450000000000074,2021-04-12,2021-04-16
CRM,231.91,14,231.91,0.0,2021-04-17,2021-04-18
MCD,233.08,14,233.01,-0.9800000000003024,2021-04-19,2021-04-21
WMT,141.2,24,139.67,-36.72000000000003,2021-04-22,2021-04-23
UNH,400.31,8,400.31,0.0,2021-04-24,2021-04-25
CSCO,51.91,64,51.11,-51.19999999999982,2021-04-26,2021-04-29
JPM,155.19,21,153.81,-28.979999999999905,2021-04-30,2021-05-01
CRM,230.32,14,230.32,0.0,2021-05-02,2021-05-03
CSCO,51.17,64,50.71,-29.440000000000055,2021-05-04,2021-05-05
WMT,140.05,23,140.2,3.449999999999477,2021-05-06,2021-05-08
HD,339.25,9,341.12,16.83000000000004,2021-05-09,2021-05-11
MSFT,246.23,13,243.03,-41.59999999999985,2021-05-12,2021-05-14
MRK,78.29,41,78.29,0.0,2021-05-15,2021-05-16
HON,227.36,14,222.32,-70.56000000000029,2021-05-17,2021-05-19
WBA,54.81,57,54.6,-11.970000000000049,2021-05-20,2021-05-21
AMGN,251.01,12,251.01,0.0,2021-05-22,2021-05-23
TRV,159.08,19,160.89,34.3899999999995,2021-05-24,2021-06-02
HD,313.23,10,311.01,-22.200000000000273,2021-06-03,2021-06-07
MSFT,253.81,12,253.59,-2.6399999999999864,2021-06-08,2021-06-10
UNH,401.49,7,397.89,-25.20000000000016,2021-06-11,2021-06-12
MRK,76.27,41,76.27,0.0,2021-06-13,2021-06-14
HON,223.17,14,222.5,-9.379999999999825,2021-06-15,2021-06-16
HD,302.78,10,302.61,-1.6999999999995907,2021-06-17,2021-06-20
MSFT,259.43,12,266.69,87.11999999999989,2021-06-21,2021-06-25
MCD,232.42,13,232.42,0.0,2021-06-26,2021-06-27
JNJ,164.21,19,168.98,90.62999999999965,2021-06-28,2021-07-03
MCD,233.63,14,233.63,0.0,2021-07-04,2021-07-06
MSFT,277.66,11,277.94,3.0799999999997,2021-07-07,2021-07-11
BA,239.59,13,222.76,-218.79000000000016,2021-07-12,2021-07-16
MRK,78.02,39,77.05,-37.829999999999956,2021-07-17,2021-07-20
MSFT,279.32,10,281.4,20.79999999999984,2021-07-21,2021-07-22
VZ,55.95,54,55.88,-3.7800000000000153,2021-07-23,2021-07-24
CSCO,55.23,55,54.77,-25.299999999999656,2021-07-25,2021-07-29
AMGN,242.46,12,241.54,-11.040000000000191,2021-07-30,2021-07-31
INTC,53.72,56,53.68,-2.2399999999999523,2021-08-01,2021-08-03
MMM,201.03,15,197.53,-52.5,2021-08-04,2021-08-05
WBA,46.93,63,48.43,94.5,2021-08-06,2021-08-11
MRK,75.21,40,76.04,33.2000000000005,2021-08-12,2021-08-13
BA,234.46,13,229.06,-70.20000000000007,2021-08-14,2021-08-17
TRV,158.9,19,158.72,-3.4200000000001296,2021-08-18,2021-08-19
CSCO,57.27,53,58.22,50.349999999999774,2021-08-20,2021-08-22
KO,56.64,54,56.44,-10.800000000000153,2021-08-23,2021-08-24
HD,324.9,9,321.48,-30.77999999999963,2021-08-25,2021-08-27
KO,55.65,54,55.65,0.0,2021-08-28,2021-08-29
CAT,212.83,14,211.45,-19.320000000000334,2021-08-30,2021-08-31
GS,413.51,7,413.66,1.0500000000002387,2021-09-01,2021-09-02
AMGN,225.96,13,226.37,5.329999999999956,2021-09-03,2021-09-04
UNH,422.86,7,422.86,0.0,2021-09-05,2021-09-06
MMM,194.39,15,185.58,-132.1499999999996,2021-09-07,2021-09-08
JNJ,171.9,16,166.97,-78.88000000000011,2021-09-09,2021-09-13
BA,214.48,13,213.36,-14.55999999999969,2021-09-14,2021-09-17
AAPL,146.06,19,146.92,16.33999999999972,2021-09-18,2021-09-25
TRV,156.46,18,156.46,0.0,2021-09-26,2021-09-27
AMGN,213.11,13,214.9,23.269999999999897,2021-09-28,2021-09-30
WBA,47.05,60,46.8,-15.0,2021-10-01,2021-10-02
IBM,136.89410448,20,136.7317266,-3.247557600000164,2021-10-03,2021-10-06
VZ,54.53,51,53.9,-32.13000000000013,2021-10-07,2021-10-08
WMT,139.66,20,139.66,0.0,2021-10-09,2021-10-10
MMM,176.95,15,175.53,-21.299999999999812,2021-10-11,2021-10-13
CRM,284.41,9,291.66,65.25,2021-10-14,2021-10-18
HD,355.01,7,358.23,22.54000000000019,2021-10-19,2021-10-21
CAT,202.14,14,200.65,-20.85999999999973,2021-10-22,2021-10-23
MSFT,309.16,9,309.16,0.0,2021-10-24,2021-10-25
CAT,202.21,14,204.09,26.319999999999936,2021-10-26,2021-10-29
MRK,88.05,32,88.05,0.0,2021-10-30,2021-10-31
BA,207.03,13,214.58,98.15000000000015,2021-11-01,2021-11-02
MSFT,333.13,8,336.44,26.480000000000018,2021-11-03,2021-11-05
CRM,307.25,9,309.96,24.389999999999816,2021-11-06,2021-11-09
PG,145.39,20,146.56,23.40000000000032,2021-11-10,2021-11-14
PG,146.56,20,147.1,10.79999999999984,2021-11-15,2021-11-18
AAPL,157.87,19,160.55,50.92000000000013,2021-11-19,2021-11-20
CVX,111.91,27,113.91,54.0,2021-11-21,2021-11-23
AAPL,161.41,19,161.94,10.070000000000022,2021-11-24,2021-11-25
HD,412.11,7,406.82,-37.03000000000014,2021-11-26,2021-11-30
UNH,444.22,7,444.34,0.8399999999996339,2021-12-01,2021-12-02
VZ,50.73,61,51.42,42.090000000000295,2021-12-03,2021-12-04
V,196.32,16,208.99,202.72000000000025,2021-12-05,2021-12-09
CRM,264.32,12,266.03,20.519999999999754,2021-12-10,2021-12-11
HD,415.4,8,405.24,-81.27999999999975,2021-12-12,2021-12-14
HON,206.68,16,209.76,49.279999999999745,2021-12-15,2021-12-16
MMM,178.31,18,174.75,-64.08000000000004,2021-12-17,2021-12-19
HD,387.98,8,395.64,61.279999999999745,2021-12-20,2021-12-23
MRK,75.73,44,76.57,36.959999999999525,2021-12-24,2021-12-28
MMM,177.64,19,178.41,14.630000000000194,2021-12-29,2021-12-30


================================================
FILE: results/LR_v1_predict_1_1/running_gains_df.csv
================================================
Date,Stock,Gain,Total
2020-12-31,,,3000
2021-01-01,WBA,0.0,3000.0
2021-01-02,,,3000.0
2021-01-03,VZ,-11.219999999999942,2988.78
2021-01-04,,,2988.78
2021-01-05,,,2988.78
2021-01-06,,,2988.78
2021-01-07,,,2988.78
2021-01-08,,,2988.78
2021-01-09,JPM,0.0,2988.78
2021-01-10,,,2988.78
2021-01-11,CRM,-49.2699999999999,2939.51
2021-01-12,,,2939.51
2021-01-13,CVX,-2.7900000000001057,2936.7200000000003
2021-01-14,,,2936.7200000000003
2021-01-15,WMT,-44.27000000000024,2892.45
2021-01-16,,,2892.45
2021-01-17,,,2892.45
2021-01-18,MSFT,160.1599999999999,3052.6099999999997
2021-01-19,,,3052.6099999999997
2021-01-20,,,3052.6099999999997
2021-01-21,,,3052.6099999999997
2021-01-22,,,3052.6099999999997
2021-01-23,HON,0.0,3052.6099999999997
2021-01-24,,,3052.6099999999997
2021-01-25,CRM,6.369999999999749,3058.9799999999996
2021-01-26,,,3058.9799999999996
2021-01-27,,,3058.9799999999996
2021-01-28,WMT,-70.34999999999988,2988.6299999999997
2021-01-29,,,2988.6299999999997
2021-01-30,,,2988.6299999999997
2021-01-31,,,2988.6299999999997
2021-02-01,GS,39.160000000000025,3027.7899999999995
2021-02-02,,,3027.7899999999995
2021-02-03,AXP,-6.500000000000128,3021.2899999999995
2021-02-04,,,3021.2899999999995
2021-02-05,AMGN,-10.800000000000068,3010.4899999999993
2021-02-06,,,3010.4899999999993
2021-02-07,NKE,0.0,3010.4899999999993
2021-02-08,,,3010.4899999999993
2021-02-09,UNH,47.61000000000018,3058.0999999999995
2021-02-10,,,3058.0999999999995
2021-02-11,CSCO,3.199999999999818,3061.2999999999993
2021-02-12,,,3061.2999999999993
2021-02-13,,,3061.2999999999993
2021-02-14,,,3061.2999999999993
2021-02-15,KO,0.0,3061.2999999999993
2021-02-16,,,3061.2999999999993
2021-02-17,VZ,159.0400000000002,3220.3399999999992
2021-02-18,,,3220.3399999999992
2021-02-19,KO,-41.58000000000023,3178.759999999999
2021-02-20,,,3178.759999999999
2021-02-21,CSCO,0.0,3178.759999999999
2021-02-22,,,3178.759999999999
2021-02-23,PG,26.99999999999996,3205.759999999999
2021-02-24,,,3205.759999999999
2021-02-25,,,3205.759999999999
2021-02-26,INTC,20.140000000000136,3225.899999999999
2021-02-27,,,3225.899999999999
2021-02-28,,,3225.899999999999
2021-03-01,CSCO,45.79500000000022,3271.6949999999993
2021-03-02,,,3271.6949999999993
2021-03-03,,,3271.6949999999993
2021-03-04,WBA,-52.36000000000021,3219.334999999999
2021-03-05,,,3219.334999999999
2021-03-06,BA,0.0,3219.334999999999
2021-03-07,,,3219.334999999999
2021-03-08,,,3219.334999999999
2021-03-09,CVX,-7.25,3212.084999999999
2021-03-10,,,3212.084999999999
2021-03-11,UNH,31.5,3243.584999999999
2021-03-12,,,3243.584999999999
2021-03-13,DIS,0.0,3243.584999999999
2021-03-14,,,3243.584999999999
2021-03-15,PG,10.500000000000398,3254.0849999999996
2021-03-16,,,3254.0849999999996
2021-03-17,MCD,59.5,3313.5849999999996
2021-03-18,,,3313.5849999999996
2021-03-19,TRV,-158.13000000000002,3155.4549999999995
2021-03-20,,,3155.4549999999995
2021-03-21,,,3155.4549999999995
2021-03-22,,,3155.4549999999995
2021-03-23,MMM,-18.23999999999978,3137.2149999999997
2021-03-24,,,3137.2149999999997
2021-03-25,JNJ,57.380000000000194,3194.595
2021-03-26,,,3194.595
2021-03-27,,,3194.595
2021-03-28,MRK,0.0,3194.595
2021-03-29,,,3194.595
2021-03-30,WBA,163.7999999999998,3358.3949999999995
2021-03-31,,,3358.3949999999995
2021-04-01,,,3358.3949999999995
2021-04-02,,,3358.3949999999995
2021-04-03,,,3358.3949999999995
2021-04-04,,,3358.3949999999995
2021-04-05,,,3358.3949999999995
2021-04-06,,,3358.3949999999995
2021-04-07,,,3358.3949999999995
2021-04-08,,,3358.3949999999995
2021-04-09,CAT,3.7800000000001432,3362.1749999999997
2021-04-10,,,3362.1749999999997
2021-04-11,,,3362.1749999999997
2021-04-12,MSFT,47.45000000000008,3409.625
2021-04-13,,,3409.625
2021-04-14,,,3409.625
2021-04-15,,,3409.625
2021-04-16,,,3409.625
2021-04-17,CRM,0.0,3409.625
2021-04-18,,,3409.625
2021-04-19,MCD,-0.9800000000003024,3408.6449999999995
2021-04-20,,,3408.6449999999995
2021-04-21,,,3408.6449999999995
2021-04-22,WMT,-36.72000000000003,3371.9249999999993
2021-04-23,,,3371.9249999999993
2021-04-24,UNH,0.0,3371.9249999999993
2021-04-25,,,3371.9249999999993
2021-04-26,CSCO,-51.19999999999982,3320.7249999999995
2021-04-27,,,3320.7249999999995
2021-04-28,,,3320.7249999999995
2021-04-29,,,3320.7249999999995
2021-04-30,JPM,-28.979999999999905,3291.7449999999994
2021-05-01,,,3291.7449999999994
2021-05-02,CRM,0.0,3291.7449999999994
2021-05-03,,,3291.7449999999994
2021-05-04,CSCO,-29.44000000000005,3262.3049999999994
2021-05-05,,,3262.3049999999994
2021-05-06,WMT,3.449999999999477,3265.7549999999987
2021-05-07,,,3265.7549999999987
2021-05-08,,,3265.7549999999987
2021-05-09,HD,16.83000000000004,3282.5849999999987
2021-05-10,,,3282.5849999999987
2021-05-11,,,3282.5849999999987
2021-05-12,MSFT,-41.59999999999985,3240.9849999999988
2021-05-13,,,3240.9849999999988
2021-05-14,,,3240.9849999999988
2021-05-15,MRK,0.0,3240.9849999999988
2021-05-16,,,3240.9849999999988
2021-05-17,HON,-70.56000000000029,3170.4249999999984
2021-05-18,,,3170.4249999999984
2021-05-19,,,3170.4249999999984
2021-05-20,WBA,-11.970000000000049,3158.454999999998
2021-05-21,,,3158.454999999998
2021-05-22,AMGN,0.0,3158.454999999998
2021-05-23,,,3158.454999999998
2021-05-24,TRV,34.3899999999995,3192.8449999999975
2021-05-25,,,3192.8449999999975
2021-05-26,,,3192.8449999999975
2021-05-27,,,3192.8449999999975
2021-05-28,,,3192.8449999999975
2021-05-29,,,3192.8449999999975
2021-05-30,,,3192.8449999999975
2021-05-31,,,3192.8449999999975
2021-06-01,,,3192.8449999999975
2021-06-02,,,3192.8449999999975
2021-06-03,HD,-22.200000000000276,3170.6449999999973
2021-06-04,,,3170.6449999999973
2021-06-05,,,3170.6449999999973
2021-06-06,,,3170.6449999999973
2021-06-07,,,3170.6449999999973
2021-06-08,MSFT,-2.6399999999999864,3168.0049999999974
2021-06-09,,,3168.0049999999974
2021-06-10,,,3168.0049999999974
2021-06-11,UNH,-25.20000000000016,3142.804999999997
2021-06-12,,,3142.804999999997
2021-06-13,MRK,0.0,3142.804999999997
2021-06-14,,,3142.804999999997
2021-06-15,HON,-9.379999999999823,3133.4249999999975
2021-06-16,,,3133.4249999999975
2021-06-17,HD,-1.6999999999995907,3131.7249999999976
2021-06-18,,,3131.7249999999976
2021-06-19,,,3131.7249999999976
2021-06-20,,,3131.7249999999976
2021-06-21,MSFT,87.11999999999989,3218.8449999999975
2021-06-22,,,3218.8449999999975
2021-06-23,,,3218.8449999999975
2021-06-24,,,3218.8449999999975
2021-06-25,,,3218.8449999999975
2021-06-26,MCD,0.0,3218.8449999999975
2021-06-27,,,3218.8449999999975
2021-06-28,JNJ,90.62999999999964,3309.474999999997
2021-06-29,,,3309.474999999997
2021-06-30,,,3309.474999999997
2021-07-01,,,3309.474999999997
2021-07-02,,,3309.474999999997
2021-07-03,,,3309.474999999997
2021-07-04,MCD,0.0,3309.474999999997
2021-07-05,,,3309.474999999997
2021-07-06,,,3309.474999999997
2021-07-07,MSFT,3.0799999999997,3312.5549999999967
2021-07-08,,,3312.5549999999967
2021-07-09,,,3312.5549999999967
2021-07-10,,,3312.5549999999967
2021-07-11,,,3312.5549999999967
2021-07-12,BA,-218.79000000000016,3093.7649999999967
2021-07-13,,,3093.7649999999967
2021-07-14,,,3093.7649999999967
2021-07-15,,,3093.7649999999967
2021-07-16,,,3093.7649999999967
2021-07-17,MRK,-37.82999999999996,3055.9349999999968
2021-07-18,,,3055.9349999999968
2021-07-19,,,3055.9349999999968
2021-07-20,,,3055.9349999999968
2021-07-21,MSFT,20.79999999999984,3076.7349999999965
2021-07-22,,,3076.7349999999965
2021-07-23,VZ,-3.7800000000000153,3072.9549999999963
2021-07-24,,,3072.9549999999963
2021-07-25,CSCO,-25.299999999999656,3047.6549999999966
2021-07-26,,,3047.6549999999966
2021-07-27,,,3047.6549999999966
2021-07-28,,,3047.6549999999966
2021-07-29,,,3047.6549999999966
2021-07-30,AMGN,-11.040000000000193,3036.614999999996
2021-07-31,,,3036.614999999996
2021-08-01,INTC,-2.2399999999999523,3034.3749999999964
2021-08-02,,,3034.3749999999964
2021-08-03,,,3034.3749999999964
2021-08-04,MMM,-52.5,2981.8749999999964
2021-08-05,,,2981.8749999999964
2021-08-06,WBA,94.5,3076.3749999999964
2021-08-07,,,3076.3749999999964
2021-08-08,,,3076.3749999999964
2021-08-09,,,3076.3749999999964
2021-08-10,,,3076.3749999999964
2021-08-11,,,3076.3749999999964
2021-08-12,MRK,33.2000000000005,3109.574999999997
2021-08-13,,,3109.574999999997
2021-08-14,BA,-70.20000000000007,3039.374999999997
2021-08-15,,,3039.374999999997
2021-08-16,,,3039.374999999997
2021-08-17,,,3039.374999999997
2021-08-18,TRV,-3.4200000000001296,3035.9549999999967
2021-08-19,,,3035.9549999999967
2021-08-20,CSCO,50.349999999999774,3086.3049999999967
2021-08-21,,,3086.3049999999967
2021-08-22,,,3086.3049999999967
2021-08-23,KO,-10.800000000000152,3075.5049999999965
2021-08-24,,,3075.5049999999965
2021-08-25,HD,-30.77999999999963,3044.7249999999967
2021-08-26,,,3044.7249999999967
2021-08-27,,,3044.7249999999967
2021-08-28,KO,0.0,3044.7249999999967
2021-08-29,,,3044.7249999999967
2021-08-30,CAT,-19.32000000000033,3025.4049999999966
2021-08-31,,,3025.4049999999966
2021-09-01,GS,1.0500000000002387,3026.4549999999967
2021-09-02,,,3026.4549999999967
2021-09-03,AMGN,5.329999999999956,3031.7849999999967
2021-09-04,,,3031.7849999999967
2021-09-05,UNH,0.0,3031.7849999999967
2021-09-06,,,3031.7849999999967
2021-09-07,MMM,-132.1499999999996,2899.634999999997
2021-09-08,,,2899.634999999997
2021-09-09,JNJ,-78.88000000000011,2820.754999999997
2021-09-10,,,2820.754999999997
2021-09-11,,,2820.754999999997
2021-09-12,,,2820.754999999997
2021-09-13,,,2820.754999999997
2021-09-14,BA,-14.55999999999969,2806.1949999999974
2021-09-15,,,2806.1949999999974
2021-09-16,,,2806.1949999999974
2021-09-17,,,2806.1949999999974
2021-09-18,AAPL,16.33999999999972,2822.534999999997
2021-09-19,,,2822.534999999997
2021-09-20,,,2822.534999999997
2021-09-21,,,2822.534999999997
2021-09-22,,,2822.534999999997
2021-09-23,,,2822.534999999997
2021-09-24,,,2822.534999999997
2021-09-25,,,2822.534999999997
2021-09-26,TRV,0.0,2822.534999999997
2021-09-27,,,2822.534999999997
2021-09-28,AMGN,23.269999999999897,2845.804999999997
2021-09-29,,,2845.804999999997
2021-09-30,,,2845.804999999997
2021-10-01,WBA,-15.0,2830.804999999997
2021-10-02,,,2830.804999999997
2021-10-03,IBM,-3.247557600000164,2827.557442399997
2021-10-04,,,2827.557442399997
2021-10-05,,,2827.557442399997
2021-10-06,,,2827.557442399997
2021-10-07,VZ,-32.13000000000013,2795.427442399997
2021-10-08,,,2795.427442399997
2021-10-09,WMT,0.0,2795.427442399997
2021-10-10,,,2795.427442399997
2021-10-11,MMM,-21.29999999999981,2774.127442399997
2021-10-12,,,2774.127442399997
2021-10-13,,,2774.127442399997
2021-10-14,CRM,65.25,2839.377442399997
2021-10-15,,,2839.377442399997
2021-10-16,,,2839.377442399997
2021-10-17,,,2839.377442399997
2021-10-18,,,2839.377442399997
2021-10-19,HD,22.54000000000019,2861.9174423999975
2021-10-20,,,2861.9174423999975
2021-10-21,,,2861.9174423999975
2021-10-22,CAT,-20.85999999999973,2841.057442399998
2021-10-23,,,2841.057442399998
2021-10-24,MSFT,0.0,2841.057442399998
2021-10-25,,,2841.057442399998
2021-10-26,CAT,26.319999999999936,2867.3774423999976
2021-10-27,,,2867.3774423999976
2021-10-28,,,2867.3774423999976
2021-10-29,,,2867.3774423999976
2021-10-30,MRK,0.0,2867.3774423999976
2021-10-31,,,2867.3774423999976
2021-11-01,BA,98.15000000000016,2965.5274423999977
2021-11-02,,,2965.5274423999977
2021-11-03,MSFT,26.480000000000015,2992.0074423999977
2021-11-04,,,2992.0074423999977
2021-11-05,,,2992.0074423999977
2021-11-06,CRM,24.389999999999816,3016.3974423999975
2021-11-07,,,3016.3974423999975
2021-11-08,,,3016.3974423999975
2021-11-09,,,3016.3974423999975
2021-11-10,PG,23.40000000000032,3039.7974423999976
2021-11-11,,,3039.7974423999976
2021-11-12,,,3039.7974423999976
2021-11-13,,,3039.7974423999976
2021-11-14,,,3039.7974423999976
2021-11-15,PG,10.79999999999984,3050.5974423999974
2021-11-16,,,3050.5974423999974
2021-11-17,,,3050.5974423999974
2021-11-18,,,3050.5974423999974
2021-11-19,AAPL,50.92000000000013,3101.5174423999974
2021-11-20,,,3101.5174423999974
2021-11-21,CVX,54.0,3155.5174423999974
2021-11-22,,,3155.5174423999974
2021-11-23,,,3155.5174423999974
2021-11-24,AAPL,10.070000000000022,3165.5874423999976
2021-11-25,,,3165.5874423999976
2021-11-26,HD,-37.03000000000014,3128.5574423999974
2021-11-27,,,3128.5574423999974
2021-11-28,,,3128.5574423999974
2021-11-29,,,3128.5574423999974
2021-11-30,,,3128.5574423999974
2021-12-01,UNH,0.8399999999996339,3129.397442399997
2021-12-02,,,3129.397442399997
2021-12-03,VZ,42.090000000000295,3171.4874423999972
2021-12-04,,,3171.4874423999972
2021-12-05,V,202.72000000000023,3374.2074423999975
2021-12-06,,,3374.2074423999975
2021-12-07,,,3374.2074423999975
2021-12-08,,,3374.2074423999975
2021-12-09,,,3374.2074423999975
2021-12-10,CRM,20.519999999999754,3394.727442399997
2021-12-11,,,3394.727442399997
2021-12-12,HD,-81.27999999999975,3313.4474423999973
2021-12-13,,,3313.4474423999973
2021-12-14,,,3313.4474423999973
2021-12-15,HON,49.27999999999975,3362.727442399997
2021-12-16,,,3362.727442399997
2021-12-17,MMM,-64.08000000000004,3298.647442399997
2021-12-18,,,3298.647442399997
2021-12-19,,,3298.647442399997
2021-12-20,HD,61.27999999999975,3359.927442399997
2021-12-21,,,3359.927442399997
2021-12-22,,,3359.927442399997
2021-12-23,,,3359.927442399997
2021-12-24,MRK,36.959999999999525,3396.8874423999964
2021-12-25,,,3396.8874423999964
2021-12-26,,,3396.8874423999964
2021-12-27,,,3396.8874423999964
2021-12-28,,,3396.8874423999964
2021-12-29,MMM,14.630000000000194,3411.5174423999965
2021-12-30,,,3411.5174423999965
2021-12-31,,,3411.5174423999965


================================================
FILE: results/model_result_summary.csv
================================================
Model,Gains,Losses,Profit,Profit Percentage,Maximum Gain,Maximum Loss
LR_v1_predict_0.7_3,2974.89,-2062.63,912.26,30.41,212.4,-196
LR_v1_predict_0.9_10,2772.61,-1963.97,808.64,26.95,163.25,-159
LR_v1_predict_0.95_21,2911.67,-1478.71,1432.96,47.77,259.93,-215
LR_v1_predict_1_1,2203.36,-1791.85,411.52,13.72,202.72,-219


================================================
FILE: stock_utils/simulator.py
================================================
import numpy as np
import math
import pandas as pd

"""
stock simulator to trade in real time. 
author - Kaneel Senevirathne
date - 1/4/2022
"""

class simulator:

    def __init__(self, capital):
        self.capital = capital
        self.initial_capital = capital #keep a copy of the initial capital
        self.total_gain = 0
        self.buy_orders = {}
        self.history = []
        #create a pandas df to save history
        cols = ['stock', 'buy_price', 'n_shares', 'sell_price', 'net_gain', 'buy_date', 'sell_date']
        self.history_df = pd.DataFrame(columns = cols)
           
    def buy(self, stock, buy_price, buy_date):
        """
        function takes buy price and the number of shares and buy the stock
        """
        #calculate the procedure
        n_shares = self.buy_percentage(buy_price)
        self.capital = self.capital - buy_price * n_shares
        self.buy_orders[stock] = [buy_price, n_shares, buy_price * n_shares, buy_date]

    def sell(self, stock, sell_price, n_shares_sell, sell_date):
        """
        function to sell stock given the stock name and number of shares
        """
        buy_price, n_shares, _, buy_date = self.buy_orders[stock]
        sell_amount = sell_price * (n_shares_sell)

        self.capital = self.capital + sell_amount

        if (n_shares - n_shares_sell) == 0: #if sold all
            self.history.append([stock, buy_price, n_shares, sell_price, buy_date, sell_date])
            del self.buy_orders[stock]
        else:
            n_shares = n_shares - n_shares_sell
            self.buy_orders[stock][1] = n_shares
            self.buy_orders[stock][2] = buy_price * n_shares

    def buy_percentage(self, buy_price, buy_perc = 1):
        """
        this function determines how much capital to spend on the stock and returns the number of shares
        """
        stock_expenditure = self.capital * buy_perc
        n_shares = math.floor(stock_expenditure / buy_price)
        return n_shares

    def trailing_stop_loss(self):
        """
        activates a trailing stop loss
        """
        pass
    
    def print_bag(self):
        """
        print current stocks holding
        """
        print ("{:<10} {:<10} {:<10} {:<10}".format('STOCK', 'BUY PRICE', 'SHARES', 'TOTAL VALUE'))
        for key, value in self.buy_orders.items():
            print("{:<10} {:<10} {:<10} {:<10}".format(key, value[0], value[1], value[2]))
        print('\n')  

    def create_summary(self, print_results = False):
        """
        create summary
        """
        if print_results:
            print ("{:<10} {:<10} {:<10} {:<10} {:<10}".format('STOCK', 'BUY PRICE', 'SHARES', 'SELL PRICE', 'NET GAIN'))    
        
        for values in self.history:
            net_gain = (values[3] - values[1]) * values[2]
            self.total_gain += net_gain
            self.history_df = self.history_df.append({'stock': values[0], 'buy_price': values[1], 'n_shares': values[2], 'sell_price': values[3]\
                 ,'net_gain': net_gain, 'buy_date': values[4], 'sell_date': values[5]}, ignore_index = True)
                    
            if print_results:
                print("{:<10} {:<10} {:<10} {:<10} {:<10}".format(values[0], values[1], values[2], values[3], np.round(net_gain, 2)))
            
    def print_summary(self):
        """
        prints the summary of results
        """
        self.create_summary(print_results = True)
        print('\n')
        print(f'Initial Balance: {self.initial_capital:.2f}')
        print(f'Final Balance: {(self.initial_capital + self.total_gain):.2f}')
        print(f'Total gain: {self.total_gain:.2f}')
        print(f'P/L : {(self.total_gain/self.initial_capital)*100:.2f} %')
        print('\n')

================================================
FILE: stock_utils/stock_utils.py
================================================
from td.client import TDClient
import requests, time, re, os
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from datetime import datetime, timedelta
from scipy.signal import argrelextrema
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import MinMaxScaler
from datetime import datetime

"""
author - Kaneel Senevirathne
date - 1/8/2022
stock utils for preparing training data.
"""

#TD API - 
TD_API = 'XXXXX' ### your TD ameritrade api key



def timestamp(dt):
    epoch = datetime.utcfromtimestamp(0)
    return int((dt - epoch).total_seconds() * 1000)


def linear_regression(x, y):
    """
    performs linear regression given x and y. outputs regression coefficient
    """
    #fit linear regression
    lr = LinearRegression()
    lr.fit(x, y)
    
    return lr.coef_[0][0]

def n_day_regression(n, df, idxs):
    """
    n day regression.
    """
    #variable
    _varname_ = f'{n}_reg'
    df[_varname_] = np.nan

    for idx in idxs:
        if idx > n:
            
            y = df['close'][idx - n: idx].to_numpy()
            x = np.arange(0, n)
            #reshape
            y = y.reshape(y.shape[0], 1)
            x = x.reshape(x.shape[0], 1)
            #calculate regression coefficient 
            coef = linear_regression(x, y)
            df.loc[idx, _varname_] = coef #add the new value
            
    return df

def normalized_values(high, low, close):
    """
    normalize the price between 0 and 1.
    """
    #epsilon to avoid deletion by 0
    epsilon = 10e-10
    
    #subtract the lows
    high = high - low
    close = close - low
    return close/(high + epsilon)

def get_stock_price(stock, date):
    """
    returns the stock price given a date
    """
    start_date = date - timedelta(days = 10)
    end_date = date
    
    #enter url of database
    url = f'https://api.tdameritrade.com/v1/marketdata/{stock}/pricehistory'

    query = {'apikey': str(TD_API), 'startDate': timestamp(start_date), \
            'endDate': timestamp(end_date), 'periodType': 'year', 'frequencyType': \
            'daily', 'frequency': '1', 'needExtendedHoursData': 'False'}

    #request
    results = requests.get(url, params = query)
    data = results.json()
    
    try:
        #change the data from ms to datetime format
        data = pd.DataFrame(data['candles'])
        data['date'] = pd.to_datetime(data['datetime'], unit = 'ms')
        return data['close'].values[-1]
    except:
        pass
    
def get_data(sym, start_date = None, end_date = None, n = 10):

    #enter url
    url = f'https://api.tdameritrade.com/v1/marketdata/{sym}/pricehistory'
    
    if start_date:
        payload = {'apikey': str(TD_API), 'startDate': timestamp(start_date), \
            'endDate': timestamp(end_date), 'periodType': 'year', 'frequencyType': \
            'daily', 'frequency': '1', 'needExtendedHoursData': 'False'}
    else:
        payload = {'apikey': str(TD_API), 'startDate': timestamp(datetime(2007, 1, 1)), \
            'endDate': timestamp(datetime(2020, 12, 31)), 'periodType': 'year', 'frequencyType': \
            'daily', 'frequency': '1', 'needExtendedHoursData': 'False'}
            
    #request
    results = requests.get(url, params = payload)
    data = results.json()
    
    #change the data from ms to datetime format
    data = pd.DataFrame(data['candles'])
    data['date'] = pd.to_datetime(data['datetime'], unit = 'ms')

    #add the noramlzied value function and create a new column
    data['normalized_value'] = data.apply(lambda x: normalized_values(x.high, x.low, x.close), axis = 1)
    
    #column with local minima and maxima
    data['loc_min'] = data.iloc[argrelextrema(data.close.values, np.less_equal, order = n)[0]]['close']
    data['loc_max'] = data.iloc[argrelextrema(data.close.values, np.greater_equal, order = n)[0]]['close']

    #idx with mins and max
    idx_with_mins = np.where(data['loc_min'] > 0)[0]
    idx_with_maxs = np.where(data['loc_max'] > 0)[0]
    
    return data, idx_with_mins, idx_with_maxs

def create_train_data(stock, start_date = None, end_date = None, n = 10):

    #get data to a dataframe
    data, idxs_with_mins, idxs_with_maxs = get_data(stock, start_date, end_date, n)
    
    #create regressions for 3, 5 and 10 days
    data = n_day_regression(3, data, list(idxs_with_mins) + list(idxs_with_maxs))
    data = n_day_regression(5, data, list(idxs_with_mins) + list(idxs_with_maxs))
    data = n_day_regression(10, data, list(idxs_with_mins) + list(idxs_with_maxs))
    data = n_day_regression(20, data, list(idxs_with_mins) + list(idxs_with_maxs))
  
    _data_ = data[(data['loc_min'] > 0) | (data['loc_max'] > 0)].reset_index(drop = True)
    
    #create a dummy variable for local_min (0) and max (1)
    _data_['target'] = [1 if x > 0 else 0 for x in _data_.loc_max]
    
    #columns of interest
    cols_of_interest = ['volume', 'normalized_value', '3_reg', '5_reg', '10_reg', '20_reg', 'target']
    _data_ = _data_[cols_of_interest]
    
    return _data_.dropna(axis = 0)

def create_test_data_lr(stock, start_date = None, end_date = None, n = 10):
    """
    this function create test data sample for logistic regression model
    """
    #get data to a dataframe
    data, _, _ = get_data(stock, start_date, end_date, n)
    idxs = np.arange(0, len(data))
    
    #create regressions for 3, 5 and 10 days
    data = n_day_regression(3, data, idxs)
    data = n_day_regression(5, data, idxs)
    data = n_day_regression(10, data, idxs)
    data = n_day_regression(20, data, idxs)
    
    cols = ['close', 'volume', 'normalized_value', '3_reg', '5_reg', '10_reg', '20_reg']
    data = data[cols]

    return data.dropna(axis = 0)

def predict_trend(stock, _model_, start_date = None, end_date = None, n = 10):

    #get data to a dataframe
    data, _, _ = get_data(stock, start_date, end_date, n)
    
    idxs = np.arange(0, len(data))
    #create regressions for 3, 5 and 10 days
    data = n_day_regression(3, data, idxs)
    data = n_day_regression(5, data, idxs)
    data = n_day_regression(10, data, idxs)
    data = n_day_regression(20, data, idxs)
        
    #create a column for predicted value
    data['pred'] = np.nan

    #get data
    cols = ['volume', 'normalized_value', '3_reg', '5_reg', '10_reg', '20_reg']
    x = data[cols]

    #scale the x data
    scaler = MinMaxScaler()
    x = scaler.fit_transform(x)

    for i in range(x.shape[0]):
        
        try:
            data['pred'][i] = _model_.predict(x[i, :])

        except:
            data['pred'][i] = np.nan

    return data