kesh-utils 0.2.6

Kesh Utils for Data science/EDA/Data preparation

Chart + Util = Chartil (Click to expand)

Chart + Util = Chartil

Data visualization: Simple, Single unified API for plotting and charting

During EDA/data preparation we use few common and fixed set of chart types to analyse the relation among various features. Few are simple charts like univariate and some are complex 3D or even multiple features>3.

This api is simple, single api to plot various type of relations which will hide all the technical/code details from Data Science task and approch. This overcomes the difficulties of maintaining several api or libraries and avoid repeated codes.

Using this approach we just need one api (Rest all decided by library)

from KUtils.eda import chartil

chartil.plot(dataframe, [list of columns]) or
chartil.plot(dataframe, [list of columns], {optional_settings})

Demo code:

Load UCI Dataset. Download From here

heart_disease_df = pd.read_csv('../input/uci/heart.csv')

Quick data preparation

column_to_convert_to_categorical = ['target', 'cp', 'fbs', 'exang', 'restecg', 'slope', 'ca', 'thal']
for col in column_to_convert_to_categorical:
	heart_disease_df[col] = heart_disease_df[col].astype('category')

heart_disease_df['age_bin'] = pd.cut(heart_disease_df['age'], [0, 32, 40, 50, 60, 70, 100], labels=['<32', '33-40','41-50','51-60','61-70', '71+'])   

heart_disease_df['sex'] = heart_disease_df['sex'].map({1:'Male', 0:'Female'})

heart_disease_df.info()

Heatmap

chartil.plot(heart_disease_df, heart_disease_df.columns) # Send all column names 

chartil.plot(heart_disease_df, heart_disease_df.columns, optional_settings={'include_categorical':True} ) 

chartil.plot(heart_disease_df, heart_disease_df.columns, optional_settings={'include_categorical':True, 'sort_by_column':'trestbps'} ) 

# Force to plot heatmap when you have fewer columns, otherwise tool will decide as different chart
chartil.plot(heart_disease_df, ['chol', 'thalach', 'trestbps'], chart_type='heatmap') 

Uni-categorical

chartil.plot(heart_disease_df, ['target']) # Barchart as count plot 

Uni-Continuous

chartil.plot(heart_disease_df, ['age'])

chartil.plot(heart_disease_df, ['age'], chart_type='barchart') # Force barchart on cntinuous by auto creating 10 equal bins 

chartil.plot(heart_disease_df, ['age'], chart_type='barchart', optional_settings={'no_of_bins':5}) # Create custom number of bins 

chartil.plot(heart_disease_df, ['age'], chart_type='distplot') 

Uni-categorical with optional_settings

chartil.plot(heart_disease_df, ['age_bin']) # Barchart as count plot

chartil.plot(heart_disease_df, ['age_bin'], optional_settings={'sort_by_value':True})

chartil.plot(heart_disease_df, ['age_bin'], optional_settings={'sort_by_value':True, 'limit_bars_count_to':5})

Bi Category vs Category (& Univariate Segmented)

chartil.plot(heart_disease_df, ['sex', 'target'])

chartil.plot(heart_disease_df, ['sex', 'target'], chart_type='crosstab')

chartil.plot(heart_disease_df, ['sex', 'target'], chart_type='stacked_barchart')

Bi Continuous vs Continuous

chartil.plot(heart_disease_df, ['chol', 'thalach']) # Scatter plot

Bi Continuous vs Category

chartil.plot(heart_disease_df, ['thalach', 'sex']) # Grouped box plot (Segmented univariate)

chartil.plot(heart_disease_df, ['thalach', 'sex'], chart_type='distplot') # Distplot

Multi 3 Continuous

chartil.plot(heart_disease_df, ['chol', 'thalach', 'trestbps']) # Colored 3D scatter plot

Multi 3 Categorical

chartil.plot(heart_disease_df, ['sex', 'age_bin', 'target']) # Paired barchart

Multi 2 Continuous, 1 Category

chartil.plot(heart_disease_df, ['chol', 'thalach', 'target']) # Scatter plot with colored groups 

Multi 1 Continuous, 2 Category

chartil.plot(heart_disease_df, ['thalach', 'sex', 'target']) # Grouped boxplot

chartil.plot(heart_disease_df, ['thalach', 'sex', 'target'], chart_type='violinplot') # Grouped violin plot

Multi 3 Continuous, 1 category

chartil.plot(heart_disease_df, ['chol', 'thalach', 'trestbps', 'target']) # Group Color highlighted 3D plot

Multi 3 Continuous, 2 category

chartil.plot(heart_disease_df, ['sex','cp','target','thalach','trestbps']) # Paired scatter plot

Auto Liner Regression (Click to expand)

Todo: