multitouch_article_pt3

multitouch_article_pt3.py

#Setting up the empty dataframe that will be filled with the attributed conversions
columns = ['date', 'utm_medium', 'conversions']
attributed_conversion_df = pd.DataFrame(columns=columns)
#looping over all the rows of the raw GA dataframe
for index, row in ga_raw_data.iterrows():
    #looking for rows that have at least 1 conversion
    if row['submitted_applications'] > 0: 
        #create a dataframe with the conversion raw and all former sessions of this user
        single_conversion_df = ga_raw_data[(ga_raw_data['date'] <= pd.to_datetime(row["date"])) & (ga_raw_data['user_id'] == row["user_id"])]
        #sorting by date and number of conversion ascending
        single_conversion_df = single_conversion_df.sort_values(by=['date', 'submitted_applications'], ascending=True) 
        #rank all the sessions in the user history (from the first one to the conversion)
        single_conversion_df['occurrences'] = single_conversion_df.groupby('user_id').cumcount() + 1 
        #set up a variable with the total number of sessions
        occurrences = single_conversion_df.loc[(single_conversion_df['submitted_applications'] == row["submitted_applications"]) & (single_conversion_df['date'] == row["date"])& (single_conversion_df['utm_medium'] == row["utm_medium"]), 'occurrences'].iloc[0] 
        #set up a value that divides the conversion(s) by the number of session
        conversion_per_row = single_conversion_df.loc[single_conversion_df['submitted_applications'] == row["submitted_applications"], 'submitted_applications'].iloc[0]/occurrences 
        #append the linear distributed conversion to each row
        single_conversion_df['conversions'] = float(conversion_per_row)
        #set the conversion date for each row
        single_conversion_df['date'] = single_conversion_df.loc[(single_conversion_df['submitted_applications'] == row["submitted_applications"]) & (single_conversion_df['date'] == row["date"])& (single_conversion_df['utm_medium'] == row["utm_medium"]), 'occurrences'].iloc[0] 
        #filter the relevant columns for the attributed dataframe
        single_conversion_df = single_conversion_df.filter(items=['date', 'utm_medium', 'conversions'])
        #append the conversion dataframe to the main dataframe
        attributed_conversion_df = attributed_conversion_df.append(single_conversion_df)

attributed_conversion_df.head(50)