salilathalye

BIM Info = 
VAR TableInfo =
    ADDCOLUMNS (
        INFO.VIEW.TABLES (),
        "Component", "Tables"
    )
VAR ColumnInfo =
    ADDCOLUMNS (
        INFO.VIEW.COLUMNS (),
        "Component", "Columns"

salilathalye

def impute_missing(df):
  '''
  Impute categorical with mode
  Impute numeric with mean
  '''
  categorical_cols = df.select_dtypes(include=['object','category']).columns
  numeric_cols = df.select_dtypes(include=['number']).columns
  for cat_col in categorical_cols:
    df[cat_col] = df[cat_col].fillna(df[cat_col].value_counts()[0])
  for num_col in numeric_cols:

salilathalye

def trim_all_columns(df):
    """
    https://stackoverflow.com/questions/40950310/strip-trim-all-strings-of-a-dataframe
    Trim whitespace from ends of each value across all series in dataframe
    """
    trim_strings = lambda x: x.strip() if isinstance(x, str) else x
    return df.applymap(trim_strings)

salilathalye

from pathlib import Path
# Uses cookiecutter datascience template
# This jupyter notebook is in the notebooks directory

notebook_path = Path('.').resolve() 
project_path = notebook_path.parents[0]
data_raw_path = project_path / 'data' / 'raw'
data_interim_path = project_path / 'data' / 'interim'
data_processed_path = project_path / 'data' / 'processed'

salilathalye

from pandas_profiling import ProfileReport
profile = ProfileReport(training_data, title='Pandas Profiling Report', explorative=True)
profile.to_file("training_data_profile.html")
profile.to_notebook_iframe()

salilathalye

def categorical_summary(df):
  '''
  Adapted from https://www.kaggle.com/nextbigwhat/eda-for-categorical-variables-part-2

  Returns a dataframe containing information about categorical columns
  Column name is set as the index
  '''
  categorical_cols = df.select_dtypes(include='object').columns
  summary_df = pd.DataFrame(columns=
      [

salilathalye

def plot_correlaton_heatmap(df):
  numeric_cols = df.select_dtypes(exclude='object').columns
  plt.figure(figsize=(10,8)) 
  sns.heatmap(df[numeric_cols].corr(), cmap='RdBu_r', annot=True) 
  print(plt.show())

salilathalye

import dtale
import dtale.app as dtale_app

dtale_app.USE_NGROK = True

dtale.show(training_data, ignore_duplicate=True)

salilathalye

cookiecutter https://github.com/drivendata/cookiecutter-data-science

salilathalye

git config --global init.defaultBranch main