SYMBOL INDEX (242 symbols across 74 files)

FILE: 03-orchestration/code/duration-prediction.py
  function read_dataframe (line 23) | def read_dataframe(year, month):
  function create_X (line 40) | def create_X(df, dv=None):
  function train_model (line 54) | def train_model(X_train, y_train, X_val, y_val, dv):
  function run (line 92) | def run(year, month):

FILE: 04-deployment/batch/score.py
  function generate_uuids (line 27) | def generate_uuids(n):
  function read_dataframe (line 34) | def read_dataframe(filename: str):
  function prepare_dictionaries (line 46) | def prepare_dictionaries(df: pd.DataFrame):
  function load_model (line 58) | def load_model(run_id):
  function save_results (line 64) | def save_results(df, y_pred, run_id, output_file):
  function apply_model (line 79) | def apply_model(input_file, run_id, output_file):
  function get_paths (line 98) | def get_paths(run_date, taxi_type, run_id):
  function ride_duration_prediction (line 110) | def ride_duration_prediction(
  function run (line 127) | def run():

FILE: 04-deployment/batch/score_backfill.py
  function ride_duration_prediction_backfill (line 10) | def ride_duration_prediction_backfill():

FILE: 04-deployment/streaming/lambda_function.py
  function prepare_features (line 22) | def prepare_features(ride):
  function predict (line 29) | def predict(features):
  function lambda_handler (line 34) | def lambda_handler(event, context):

FILE: 04-deployment/web-service-mlflow/predict.py
  function prepare_features (line 15) | def prepare_features(ride):
  function predict (line 22) | def predict(features):
  function predict_endpoint (line 31) | def predict_endpoint():

FILE: 04-deployment/web-service/predict.py
  function prepare_features (line 9) | def prepare_features(ride):
  function predict (line 16) | def predict(features):
  function predict_endpoint (line 26) | def predict_endpoint():

FILE: 05-monitoring/dummy_metrics_calculation.py
  function prep_db (line 26) | def prep_db():
  function calculate_dummy_metrics_postgresql (line 34) | def calculate_dummy_metrics_postgresql(curr):
  function main (line 44) | def main():

FILE: 05-monitoring/evidently_metrics_calculation.py
  function prep_db (line 56) | def prep_db():
  function calculate_metrics_postgresql (line 65) | def calculate_metrics_postgresql(curr, i):
  function batch_monitoring_backfill (line 87) | def batch_monitoring_backfill():

FILE: 05-monitoring/post-evidently-0.7/dummy_metrics_calculation.py
  function prep_db (line 26) | def prep_db():
  function calculate_dummy_metrics_postgresql (line 34) | def calculate_dummy_metrics_postgresql(curr):
  function main (line 44) | def main():

FILE: 05-monitoring/post-evidently-0.7/evidently_metrics_calculation.py
  function prep_db (line 60) | def prep_db():
  function calculate_metrics_postgresql (line 69) | def calculate_metrics_postgresql(i):
  function batch_monitoring_backfill (line 94) | def batch_monitoring_backfill():

FILE: 06-best-practices/code/lambda_function.py
  function lambda_handler (line 17) | def lambda_handler(event, context):

FILE: 06-best-practices/code/model.py
  function get_model_location (line 9) | def get_model_location(run_id):
  function load_model (line 22) | def load_model(run_id):
  function base64_decode (line 28) | def base64_decode(encoded_data):
  class ModelService (line 34) | class ModelService:
    method __init__ (line 35) | def __init__(self, model, model_version=None, callbacks=None):
    method prepare_features (line 40) | def prepare_features(self, ride):
    method predict (line 46) | def predict(self, features):
    method lambda_handler (line 50) | def lambda_handler(self, event):
  class KinesisCallback (line 80) | class KinesisCallback:
    method __init__ (line 81) | def __init__(self, kinesis_client, prediction_stream_name):
    method put_record (line 85) | def put_record(self, prediction_event):
  function create_kinesis_client (line 95) | def create_kinesis_client():
  function init (line 104) | def init(prediction_stream_name: str, run_id: str, test_run: bool):

FILE: 06-best-practices/code/tests/model_test.py
  function read_text (line 6) | def read_text(file):
  function test_base64_decode (line 13) | def test_base64_decode():
  function test_prepare_features (line 29) | def test_prepare_features():
  class ModelMock (line 48) | class ModelMock:
    method __init__ (line 49) | def __init__(self, value):
    method predict (line 52) | def predict(self, X):
  function test_predict (line 57) | def test_predict():
  function test_lambda_handler (line 72) | def test_lambda_handler():

FILE: cohorts/2022/02-experiment-tracking/homework/hpo.py
  function load_pickle (line 16) | def load_pickle(filename):
  function run (line 21) | def run(data_path, num_trials):

FILE: cohorts/2022/02-experiment-tracking/homework/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run (line 39) | def run(raw_data_path: str, dest_path: str, dataset: str = "green"):

FILE: cohorts/2022/02-experiment-tracking/homework/register_model.py
  function load_pickle (line 29) | def load_pickle(filename):
  function train_and_log_model (line 34) | def train_and_log_model(data_path, params):
  function run (line 51) | def run(data_path, log_top):

FILE: cohorts/2022/02-experiment-tracking/homework/train.py
  function load_pickle (line 9) | def load_pickle(filename: str):
  function run (line 14) | def run(data_path):

FILE: cohorts/2022/03-orchestration/code/model_training.py
  function read_dataframe (line 19) | def read_dataframe(filename):
  function add_features (line 35) | def add_features(train_path="./data/green_tripdata_2021-01.parquet",
  function train_model_search (line 93) | def train_model_search(train, valid, y_val):
  function train_best_model (line 130) | def train_best_model(train, valid, y_val, dv):

FILE: cohorts/2022/03-orchestration/code/orchestration.py
  function read_dataframe (line 18) | def read_dataframe(filename):
  function add_features (line 35) | def add_features(df_train, df_val):
  function train_model_search (line 58) | def train_model_search(train, valid, y_val):
  function train_best_model (line 96) | def train_best_model(X_train, X_val, y_train, y_val, dv):
  function main_flow (line 133) | def main_flow(train_path: str = './data/green_tripdata_2021-01.parquet',

FILE: cohorts/2022/03-orchestration/code/prefect_deploy.py
  function read_dataframe (line 17) | def read_dataframe(filename):
  function add_features (line 34) | def add_features(df_train, df_val):
  function train_model_search (line 62) | def train_model_search(train, valid, y_val):
  function train_best_model (line 100) | def train_best_model(train, valid, y_val, dv):
  function main (line 134) | def main(train_path: str="./data/green_tripdata_2021-01.parquet",

FILE: cohorts/2022/03-orchestration/code/prefect_flow.py
  function read_dataframe (line 17) | def read_dataframe(filename):
  function add_features (line 34) | def add_features(df_train, df_val):
  function train_model_search (line 62) | def train_model_search(train, valid, y_val):
  function train_best_model (line 100) | def train_best_model(train, valid, y_val, dv):
  function main (line 134) | def main(train_path: str="./data/green_tripdata_2021-01.parquet",

FILE: cohorts/2022/03-orchestration/code/work-queue.py
  function myflow (line 4) | def myflow():

FILE: cohorts/2022/03-orchestration/homework.py
  function read_data (line 7) | def read_data(path):
  function prepare_features (line 11) | def prepare_features(df, categorical, train=True):
  function train_model (line 25) | def train_model(df, categorical):
  function run_model (line 42) | def run_model(df, categorical, dv, lr):
  function main (line 52) | def main(train_path: str = './data/fhv_tripdata_2021-01.parquet',

FILE: cohorts/2022/03-orchestration/homework_solution.py
  function read_data (line 12) | def read_data(path):
  function prepare_features (line 17) | def prepare_features(df, categorical, train=True):
  function train_model (line 33) | def train_model(df, categorical):
  function run_model (line 51) | def run_model(df, categorical, dv, lr):
  function get_paths (line 63) | def get_paths(date):
  function main (line 76) | def main(date=None):

FILE: cohorts/2022/04-deployment/homework/batch.py
  function read_data (line 22) | def read_data(filename):

FILE: cohorts/2022/05-monitoring/homework/model_training.py
  function read_dataframe (line 9) | def read_dataframe(filename):
  function add_features (line 25) | def add_features(train_data="./datasets/green_tripdata_2021-03.parquet",

FILE: cohorts/2022/05-monitoring/homework/prediction_service/app.py
  function prepare_features (line 28) | def prepare_features(ride):
  function save_db (line 39) | def save_db(record, pred_result):
  function get_info (line 49) | def get_info():
  function predict_duration (line 66) | def predict_duration():

FILE: cohorts/2022/05-monitoring/homework/prefect-monitoring/prefect_monitoring.py
  function upload_target (line 25) | def upload_target(filename):
  function load_reference_data (line 38) | def load_reference_data(filename):
  function fetch_data (line 57) | def fetch_data():
  function run_evidently (line 64) | def run_evidently(ref_data, data):
  function save_report (line 81) | def save_report(result):
  function save_html_report (line 85) | def save_html_report(result):
  function batch_analyze (line 90) | def batch_analyze():

FILE: cohorts/2022/05-monitoring/homework/prefect-monitoring/prefect_monitoring_solution.py
  function upload_target (line 26) | def upload_target(filename):
  function load_reference_data (line 39) | def load_reference_data(filename):
  function fetch_data (line 58) | def fetch_data():
  function run_evidently (line 65) | def run_evidently(ref_data, data):
  function save_report (line 82) | def save_report(result):
  function save_html_report (line 90) | def save_html_report(result, filename_suffix=None):
  function batch_analyze (line 100) | def batch_analyze():

FILE: cohorts/2022/05-monitoring/homework/prefect-monitoring/send_data.py
  class DateTimeEncoder (line 14) | class DateTimeEncoder(json.JSONEncoder):
    method default (line 15) | def default(self, o):

FILE: cohorts/2022/06-best-practices/homework/batch.py
  function read_data (line 22) | def read_data(filename):

FILE: cohorts/2022/06-best-practices/homework_solution/batch.py
  function prepare_data (line 10) | def prepare_data(df, categorical):
  function read_data (line 20) | def read_data(filename, categorical):
  function write_date (line 37) | def write_date(filename, df):
  function get_input_path (line 52) | def get_input_path(year, month):
  function get_output_path (line 58) | def get_output_path(year, month):
  function main (line 64) | def main(year, month):

FILE: cohorts/2022/06-best-practices/homework_solution/integration_test.py
  function dt (line 8) | def dt(hour, minute, second=0):

FILE: cohorts/2022/06-best-practices/homework_solution/tests/test_batch.py
  function dt (line 8) | def dt(hour, minute, second=0):
  function test_prepare_data (line 12) | def test_prepare_data():

FILE: cohorts/2023/02-experiment-tracking/homework-wandb/preprocess_data.py
  function dump_pickle (line 11) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 16) | def read_dataframe(filename: str):
  function preprocess (line 29) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(

FILE: cohorts/2023/02-experiment-tracking/homework-wandb/sweep.py
  function load_pickle (line 12) | def load_pickle(filename: str):
  function run_train (line 17) | def run_train(data_artifact: str):
  function run_sweep (line 81) | def run_sweep(wandb_project: str, wandb_entity: str, data_artifact: str,...

FILE: cohorts/2023/02-experiment-tracking/homework-wandb/train.py
  function load_pickle (line 11) | def load_pickle(filename: str):
  function run_train (line 25) | def run_train(

FILE: cohorts/2023/02-experiment-tracking/homework/hpo.py
  function load_pickle (line 15) | def load_pickle(filename):
  function run_optimization (line 31) | def run_optimization(data_path: str, num_trials: int):

FILE: cohorts/2023/02-experiment-tracking/homework/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(raw_data_path: str, dest_path: str, dataset: str = "gr...

FILE: cohorts/2023/02-experiment-tracking/homework/register_model.py
  function load_pickle (line 20) | def load_pickle(filename):
  function train_and_log_model (line 25) | def train_and_log_model(data_path, params):
  function run_register_model (line 56) | def run_register_model(data_path: str, top_n: int):

FILE: cohorts/2023/02-experiment-tracking/homework/train.py
  function load_pickle (line 9) | def load_pickle(filename: str):
  function run_train (line 20) | def run_train(data_path: str):

FILE: cohorts/2023/02-experiment-tracking/solution-mlflow/hpo.py
  function load_pickle (line 15) | def load_pickle(filename):
  function run_optimization (line 31) | def run_optimization(data_path: str, num_trials: int):

FILE: cohorts/2023/02-experiment-tracking/solution-mlflow/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(raw_data_path: str, dest_path: str, dataset: str = "gr...

FILE: cohorts/2023/02-experiment-tracking/solution-mlflow/register_model.py
  function load_pickle (line 20) | def load_pickle(filename):
  function train_and_log_model (line 25) | def train_and_log_model(data_path, params):
  function run_register_model (line 56) | def run_register_model(data_path: str, top_n: int):

FILE: cohorts/2023/02-experiment-tracking/solution-mlflow/train.py
  function load_pickle (line 14) | def load_pickle(filename: str):
  function run_train (line 25) | def run_train(data_path: str):

FILE: cohorts/2023/03-orchestration/prefect/3.2/cat_dog_facts.py
  function fetch_cat_fact (line 5) | def fetch_cat_fact():
  function fetch_dog_fact (line 10) | def fetch_dog_fact():
  function animal_facts (line 18) | def animal_facts():

FILE: cohorts/2023/03-orchestration/prefect/3.2/cat_facts.py
  function fetch_cat_fact (line 6) | def fetch_cat_fact():
  function fetch (line 15) | def fetch():

FILE: cohorts/2023/03-orchestration/prefect/3.3/orchestrate.py
  function read_data (line 15) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 34) | def add_features(
  function train_best_model (line 66) | def train_best_model(
  function main_flow (line 113) | def main_flow(

FILE: cohorts/2023/03-orchestration/prefect/3.3/orchestrate_pre_prefect.py
  function read_data (line 14) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 32) | def add_features(
  function train_best_model (line 63) | def train_best_model(
  function main_flow (line 109) | def main_flow(

FILE: cohorts/2023/03-orchestration/prefect/3.4/orchestrate.py
  function read_data (line 15) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 34) | def add_features(
  function train_best_model (line 66) | def train_best_model(
  function main_flow (line 113) | def main_flow(

FILE: cohorts/2023/03-orchestration/prefect/3.5/create_s3_bucket_block.py
  function create_aws_creds_block (line 5) | def create_aws_creds_block():
  function create_s3_bucket_block (line 12) | def create_s3_bucket_block():

FILE: cohorts/2023/03-orchestration/prefect/3.5/orchestrate.py
  function read_data (line 15) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 34) | def add_features(
  function train_best_model (line 66) | def train_best_model(
  function main_flow (line 113) | def main_flow(

FILE: cohorts/2023/03-orchestration/prefect/3.5/orchestrate_s3.py
  function read_data (line 18) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 37) | def add_features(
  function train_best_model (line 69) | def train_best_model(
  function main_flow_s3 (line 134) | def main_flow_s3(

FILE: cohorts/2023/03-orchestration/prefect/3.6/create_s3_bucket_block.py
  function create_aws_creds_block (line 5) | def create_aws_creds_block():
  function create_s3_bucket_block (line 12) | def create_s3_bucket_block():

FILE: cohorts/2023/03-orchestration/prefect/3.6/orchestrate_s3.py
  function read_data (line 18) | def read_data(filename: str) -> pd.DataFrame:
  function add_features (line 37) | def add_features(
  function train_best_model (line 69) | def train_best_model(
  function main_flow_s3 (line 134) | def main_flow_s3(

FILE: cohorts/2023/06-best-practices/homework/batch.py
  function read_data (line 22) | def read_data(filename):

FILE: cohorts/2023/06-best-practices/homework_solution/batch.py
  function prepare_data (line 10) | def prepare_data(df, categorical):
  function read_data (line 21) | def read_data(filename, categorical):
  function save_data (line 38) | def save_data(filename, df):
  function get_input_path (line 53) | def get_input_path(year, month):
  function get_output_path (line 59) | def get_output_path(year, month):
  function main (line 65) | def main(year, month):

FILE: cohorts/2023/06-best-practices/homework_solution/integration_test.py
  function dt (line 8) | def dt(hour, minute, second=0):

FILE: cohorts/2023/06-best-practices/homework_solution/tests/test_batch.py
  function dt (line 7) | def dt(hour, minute, second=0):
  function test_prepare_data (line 11) | def test_prepare_data():

FILE: cohorts/2024/02-experiment-tracking/homework/hpo.py
  function load_pickle (line 15) | def load_pickle(filename: str):
  function run_optimization (line 31) | def run_optimization(data_path: str, num_trials: int):

FILE: cohorts/2024/02-experiment-tracking/homework/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(raw_data_path: str, dest_path: str, dataset: str = "gr...

FILE: cohorts/2024/02-experiment-tracking/homework/register_model.py
  function load_pickle (line 20) | def load_pickle(filename):
  function train_and_log_model (line 25) | def train_and_log_model(data_path, params):
  function run_register_model (line 57) | def run_register_model(data_path: str, top_n: int):

FILE: cohorts/2024/02-experiment-tracking/homework/train.py
  function load_pickle (line 9) | def load_pickle(filename: str):
  function run_train (line 20) | def run_train(data_path: str):

FILE: cohorts/2024/02-experiment-tracking/solution/hpo.py
  function load_pickle (line 15) | def load_pickle(filename: str):
  function run_optimization (line 31) | def run_optimization(data_path: str, num_trials: int):

FILE: cohorts/2024/02-experiment-tracking/solution/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(raw_data_path: str, dest_path: str, dataset: str = "gr...

FILE: cohorts/2024/02-experiment-tracking/solution/register_model.py
  function load_pickle (line 20) | def load_pickle(filename):
  function train_and_log_model (line 25) | def train_and_log_model(data_path, params):
  function run_register_model (line 56) | def run_register_model(data_path: str, top_n: int):

FILE: cohorts/2024/02-experiment-tracking/solution/train.py
  function load_pickle (line 14) | def load_pickle(filename: str):
  function run_train (line 25) | def run_train(data_path: str):

FILE: cohorts/2024/04-deployment/homework_solution/batch.py
  function read_data (line 25) | def read_data(filename):

FILE: cohorts/2024/06-best-practices/homework/batch.py
  function read_data (line 22) | def read_data(filename):

FILE: cohorts/2025/02-experiment-tracking/homework/hpo.py
  function load_pickle (line 15) | def load_pickle(filename: str):
  function run_optimization (line 31) | def run_optimization(data_path: str, num_trials: int):

FILE: cohorts/2025/02-experiment-tracking/homework/preprocess_data.py
  function dump_pickle (line 9) | def dump_pickle(obj, filename: str):
  function read_dataframe (line 14) | def read_dataframe(filename: str):
  function preprocess (line 27) | def preprocess(df: pd.DataFrame, dv: DictVectorizer, fit_dv: bool = False):
  function run_data_prep (line 48) | def run_data_prep(raw_data_path: str, dest_path: str, dataset: str = "gr...

FILE: cohorts/2025/02-experiment-tracking/homework/register_model.py
  function load_pickle (line 20) | def load_pickle(filename):
  function train_and_log_model (line 25) | def train_and_log_model(data_path, params):
  function run_register_model (line 57) | def run_register_model(data_path: str, top_n: int):

FILE: cohorts/2025/02-experiment-tracking/homework/train.py
  function load_pickle (line 9) | def load_pickle(filename: str):
  function run_train (line 20) | def run_train(data_path: str):

FILE: cohorts/2025/06-best-practices/homework/batch.py
  function read_data (line 22) | def read_data(filename):