SYMBOL INDEX (50 symbols across 10 files)

FILE: 02_analytical_data_prep/src/DataPreperation.py
  class DataPreperation (line 1) | class DataPreperation(object):
    method __init__ (line 2) | def __init__(self):
    method label_encoder (line 6) | def label_encoder(dataframe,columns=[],frame_type='spark'):
    method imputer (line 73) | def imputer(dataframe,columns=[], type='median',frame_type='spark'):
    method polynomial_expansion (line 145) | def polynomial_expansion(dataframe,columns=[], degree=3,frame_type='sp...
    method get_top_correlations (line 249) | def get_top_correlations(dataframe,columns,frame_type='spark'):
    method feature_combiner (line 287) | def feature_combiner(training_frame, valid_frame = None, test_frame=No...
    method shrunken_averages_encoder (line 432) | def shrunken_averages_encoder(training_frame, valid_frame = None,test_...
    method convert_boolean_to_int (line 778) | def convert_boolean_to_int(frame, rejects=[],frame_type='spark'):
    method get_type_lists (line 801) | def get_type_lists(frame, rejects=['Id', 'ID','id'],frame_type='spark'):
    method remove_outliers_by_percentile (line 839) | def remove_outliers_by_percentile(dataframe, columns, limits =.01, fra...
    method winsorize_columns (line 904) | def winsorize_columns(dataframe, columns, winzerize_type='percentile',...
    method remove_outliers_by_std (line 1004) | def remove_outliers_by_std(dataframe, columns, standard_deviation_limi...
    method create_spark_estimator_vector (line 1064) | def create_spark_estimator_vector(df, ignore = [], out_put_column='fea...
    method dimensionality_reduction (line 1081) | def dimensionality_reduction(train_frame,valid_frame=None,test_frame=N...
    method pca (line 1492) | def pca(frame,columns=[],k=320,frame_type='spark'):

FILE: 03_regression/src/spark_kaggle_starter/feature_combiner.py
  function feature_combiner (line 7) | def feature_combiner(training_frame, test_frame, nums, valid_frame = Non...

FILE: 03_regression/src/spark_kaggle_starter/get_type_lists.py
  function get_type_lists (line 1) | def get_type_lists(frame, rejects=['Id', 'ID','id'],frame_type='h2o'):

FILE: 03_regression/src/spark_kaggle_starter/logging_lib/LoggingController.py
  class LoggingController (line 8) | class LoggingController(object):
    method __init__ (line 13) | def __init__(self, profile_name = 'default', s3_bucket = 'emr-related-...
    method get_datetime_str (line 20) | def get_datetime_str(self):
    method get_path_for_new_log (line 25) | def get_path_for_new_log(self):
    method log_matplotlib_plot (line 30) | def log_matplotlib_plot(self,plot, format = 'png'):
    method log_string (line 53) | def log_string(self,string):

FILE: 03_regression/src/spark_kaggle_starter/logging_lib/MarkdownBuilder.py
  class MarkdownBuilder (line 10) | class MarkdownBuilder(object):
    method __init__ (line 15) | def __init__(self, profile_name = 'default', s3_bucket = 'emr-related-...
    method get_datetime_str (line 22) | def get_datetime_str(self):
    method log_string (line 28) | def log_string(self,string):
    method build_markdowns (line 34) | def build_markdowns(self):

FILE: 03_regression/src/spark_kaggle_starter/spark_controler/emr_controller.py
  class EMRController (line 22) | class EMRController(object):
    method __init__ (line 23) | def __init__(self, profile_name = 'default', aws_access_key = False, a...
    method boto_client (line 49) | def boto_client(self, service):
    method load_cluster (line 64) | def load_cluster(self, _spark_properties=False):
    method add_create_step (line 325) | def add_create_step(self, job_flow_id, master_dns):
    method add_spark_submit_step (line 361) | def add_spark_submit_step(self, job_flow_id,name_of_script_directory):
    method create_bucket_on_s3 (line 416) | def create_bucket_on_s3(self, bucket_name):
    method upload_to_s3 (line 431) | def upload_to_s3(self, path_to_file, bucket_name, path_on_s3):
    method get_maximum_resource_allocation_properties (line 452) | def get_maximum_resource_allocation_properties(self,_master_memory,_ma...
    method get_datetime_str (line 505) | def get_datetime_str(self):
    method generate_job_name (line 511) | def generate_job_name(self):
    method tar_python_script (line 520) | def tar_python_script(self):
    method remove_temp_files (line 536) | def remove_temp_files(self, s3):
    method run (line 549) | def run(self,execute_type='create'):
    method step_copy_data_between_s3_and_hdfs (line 642) | def step_copy_data_between_s3_and_hdfs(self, c, src, dest):

FILE: 03_regression/src/spark_kaggle_starter/spark_main.py
  function glm_grid (line 170) | def glm_grid(X, y, train, valid, should_submit = False):
  function neural_net_grid (line 225) | def neural_net_grid(X, y, train, valid):
  function gboosting_grid (line 258) | def gboosting_grid(X, y, train, valid):

FILE: 03_regression/src/spark_kaggle_starter/target_encoder.py
  function target_encoder (line 1) | def target_encoder(training_frame, test_frame, x, y, lambda_=0.15, thres...

FILE: 03_regression/src/target_encoder.py
  function target_encoder (line 5) | def target_encoder(training_frame, test_frame, x, y, lambda_=0.15, thres...

FILE: cold_call.py
  function main (line 9) | def main(argv):