House_Prices_Adv_Reg_EDA

altair_EDA.py

import altair as alt
import pandas as pd

# Ignore size limits
alt.data_transformers.enable('default', max_rows=None)

# Create a function that takes the dataset and column name and returns an interactive histogram
def chart(dataset, column_name, target_var):
    w = 500
    single = alt.selection_single()
    
    # Histogram/barchart
        # If categorical don't bin
    if (column_name in dataset.select_dtypes(include='object').columns.to_list()):
        a = alt.Chart(dataset).mark_bar().encode(
        alt.X(column_name + ':N', bin=False),
        alt.Y('count()'),
        color = alt.condition(single, alt.value('#4c78a8'), alt.value('lightgray')),
        tooltip=['count()', alt.Tooltip(column_name, bin=False)]
        ).add_selection(single).properties(width=w)
    else: //# bin if numerical
        a = alt.Chart(dataset).mark_bar().encode(
        alt.X(column_name + ':Q', bin=True),
        alt.Y('count()'),
        color = alt.condition(single, alt.value('#4c78a8'), alt.value('lightgray')),
        tooltip=['count()', alt.Tooltip(column_name, bin=True)]
        ).add_selection(single).properties(width=w)
    
    # Where possible, create a boxplot for categorical variables and a scatterplot of numeric variables against target
    try:        
        if (column_name in dataset.select_dtypes(include='object').columns.to_list()):
            b = alt.Chart(dataset).mark_boxplot().encode( #, title="Boxplot of " + column_name
            alt.X(column_name + ':N'),
            alt.Y(target_var),
            color = alt.condition(single, alt.value('#4c78a8'), alt.value('lightgray')),
            tooltip=[target_var]
            ).add_selection(single).properties(width=w)
        else:
            b = alt.Chart(dataset).mark_point().encode(
            alt.X(column_name + ':Q'),
            alt.Y(target_var),
            color = alt.condition(single, alt.value('#4c78a8'), alt.value('lightgray')),
            tooltip=[target_var]
            ).add_selection(single).properties(width=w)
    except:
        pass
    
    return(a | b)