generalize statistics

Descriptive_statistics/generate_stat_desc.py

@@ -0,0 +1,58 @@
+import pandas as pd
+import numpy as np
+import os
+import s3fs
+import re
+import warnings
+
+# Ignore warning
+warnings.filterwarnings('ignore')
+
+exec(open('../0_KPI_functions.py').read())
+exec(open('plot.py').read())
+
+# Create filesystem object
+S3_ENDPOINT_URL = "https://" + os.environ["AWS_S3_ENDPOINT"]
+fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})
+
+companies = {'musee' : ['1', '2', '3', '4'], # , '101'
+            'sport': ['5'],
+            'musique' : ['10', '11', '12', '13', '14']}
+
+
+type_of_activity = input('Choisissez le type de compagnie : sport ? musique ? musee ?')
+list_of_comp = companies[type_of_activity] 
+
+# Load files
+customer, campaigns_kpi, campaigns_brut, tickets, products = load_files(list_of_comp)
+
+# Identify anonymous customer for each company and remove them from our datasets
+outlier_list = outlier_detection(tickets, list_of_comp)
+
+# Identify valid customer (customer who bought tickets after starting date)
+customer_valid_list = valid_customer_detection(products)
+
+databases = [customer, campaigns_kpi, campaigns_brut, tickets, products]
+
+for dataset in databases:
+    dataset['customer_id'] = dataset['customer_id'].apply(lambda x: remove_elements(x, outlier_list))# remove outlier
+    dataset['customer_id'] = dataset['customer_id'].isin(customer_valid_list) # keep only valid customer
+    
+# Generate graph and automatically saved them in the bucket
+compute_nb_clients(customer, type_of_activity)
+
+maximum_price_paid(customer, type_of_activity)
+
+mailing_consent(customer, type_of_activity)
+
+gender_bar(customer, type_of_activity)
+
+country_bar(customer, type_of_activity)
+
+lazy_customer_plot(campaigns_kpi, type_of_activity)
+
+campaigns_effectiveness(customer, type_of_activity)
+
+sale_dynamics(products, campaigns_brut, type_of_activity)
+
+tickets_internet(tickets, type_of_activity)

Descriptive_statistics/plot.py

@@ -0,0 +1,290 @@
+import pandas as pd
+import os
+import s3fs
+import warnings
+from datetime import date, timedelta, datetime
+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib.dates as mdates
+import seaborn as sns
+
+
+def load_files(nb_compagnie):
+    customer = pd.DataFrame()
+    campaigns_brut = pd.DataFrame()
+    campaigns_kpi = pd.DataFrame()
+    products = pd.DataFrame()
+    tickets = pd.DataFrame()
+    
+    # début de la boucle permettant de générer des datasets agrégés pour les 5 compagnies de spectacle
+    for directory_path in nb_compagnie:
+        df_customerplus_clean_0 = display_databases(directory_path, file_name = "customerplus_cleaned")
+        df_campaigns_brut = display_databases(directory_path, file_name = "campaigns_information", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])
+        df_products_purchased_reduced = display_databases(directory_path, file_name = "products_purchased_reduced", datetime_col = ['purchase_date'])
+        df_target_information = display_databases(directory_path, file_name = "target_information")
+        
+        df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_brut) 
+        df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_reduced)
+        df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)
+    
+            
+    # creation de la colonne Number compagnie, qui permettra d'agréger les résultats
+        df_tickets_kpi["number_company"]=int(directory_path)
+        df_campaigns_brut["number_company"]=int(directory_path)
+        df_campaigns_kpi["number_company"]=int(directory_path)
+        df_customerplus_clean["number_company"]=int(directory_path)
+        df_target_information["number_company"]=int(directory_path)
+    
+    # Traitement des index
+        df_tickets_kpi["customer_id"]= directory_path + '_' +  df_tickets_kpi['customer_id'].astype('str')
+        df_campaigns_brut["customer_id"]= directory_path + '_' +  df_campaigns_brut['customer_id'].astype('str')
+        df_campaigns_kpi["customer_id"]= directory_path + '_' +  df_campaigns_kpi['customer_id'].astype('str') 
+        df_customerplus_clean["customer_id"]= directory_path + '_' +  df_customerplus_clean['customer_id'].astype('str') 
+        df_products_purchased_reduced["customer_id"]= directory_path + '_' +  df_products_purchased_reduced['customer_id'].astype('str') 
+    
+    # Concaténation
+        customer = pd.concat([customer, df_customerplus_clean], ignore_index=True)
+        campaigns_kpi = pd.concat([campaigns_kpi, df_campaigns_kpi], ignore_index=True)
+        campaigns_brut = pd.concat([campaigns_brut, df_campaigns_brut], ignore_index=True) 
+        tickets = pd.concat([tickets, df_tickets_kpi], ignore_index=True)
+        products = pd.concat([products, df_products_purchased_reduced], ignore_index=True)
+
+    return customer, campaigns_kpi, campaigns_brut, tickets, products
+
+
+def save_file_s3(File_name, type_of_activity):
+    FILE_PATH = f"projet-bdc2324-team1/stat_desc/{type_of_activity}/"
+    FILE_PATH_OUT_S3 = FILE_PATH + File_name + type_of_activity + 'png'
+    with fs.open(FILE_PATH_OUT_S3, 'wb') as file_out:
+        plt.savefig(file_out)
+
+
+def outlier_detection(tickets, company_list, show_diagram=False):
+
+    outlier_list = list()
+    
+    for company in company_list:
+        total_amount_share = tickets[tickets['number_company']==int(company)].groupby('customer_id')['total_amount'].sum().reset_index()
+        total_amount_share['CA'] = total_amount_share['total_amount'].sum()
+        total_amount_share['share_total_amount'] = total_amount_share['total_amount']/total_amount_share['CA']
+        
+        total_amount_share_index = total_amount_share.set_index('customer_id')
+        df_circulaire = total_amount_share_index['total_amount'].sort_values(axis = 0, ascending = False)
+        print('df circulaire : ', df_circulaire.head())
+        top = df_circulaire[:1]
+        print('top : ', top)
+        outlier_list.append(top.index[0])
+        rest = df_circulaire[1:]
+    
+        rest_sum = rest.sum()
+        
+        new_series = pd.concat([top, pd.Series([rest_sum], index=['Autre'])])
+        
+        if show_diagram:
+            plt.figure(figsize=(3, 3))
+            plt.pie(new_series, labels=new_series.index, autopct='%1.1f%%', startangle=140, pctdistance=0.5)
+            plt.axis('equal')
+            plt.title(f'Répartition des montants totaux pour la compagnie {company}')
+            plt.show()
+    return outlier_list
+
+
+def valid_customer_detection(products):
+    products_valid = products[products['purchase_date']>="2021-05-01"]
+    consumer_valid = products_valid['customer_id'].to_list()
+    return consumer_valid
+
+def remove_elements(lst, elements_to_remove):
+    return ''.join([x for x in lst if x not in elements_to_remove])
+
+def keep_elements(lst, elements_to_remove):
+    return ''.join([x for x in lst if x in elements_to_remove])
+    
+
+def compute_nb_clients(customer, type_of_activity):
+    company_nb_clients = customer[customer["purchase_count"]>0].groupby("number_company")["customer_id"].count().reset_index()
+    plt.bar(company_nb_clients["number_company"], company_nb_clients["customer_id"]/1000)
+
+    plt.xlabel('Company')
+    plt.ylabel("Number of clients (thousands)")
+    plt.title(f"Number of clients for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("nb_clients_", type_of_activity)
+
+
+def maximum_price_paid(customer, type_of_activity):
+    company_max_price = customer.groupby("number_company")["max_price"].max().reset_index()
+    plt.bar(company_max_price["number_company"], company_max_price["max_price"])
+    
+    plt.xlabel('Company')
+    plt.ylabel("Maximal price of a ticket Prix")
+    plt.title(f"Maximal price of a ticket for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("Maximal_price_", type_of_activity)
+
+
+def mailing_consent(customer, type_of_activity):
+    df_graph = customer.groupby(["number_company", "already_purchased"])["opt_in"].mean().reset_index()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    
+    categories = df_graph["number_company"].unique()
+    bar_width = 0.35
+    bar_positions = np.arange(len(categories))
+    
+    for label in df_graph["already_purchased"].unique():
+        label_data = df_graph[df_graph['already_purchased'] == label]
+        values = [label_data[label_data['number_company'] == category]['opt_in'].values[0]*100 for category in categories]
+    
+        label_printed = "purchased" if label else "no purchase"
+        ax.bar(bar_positions, values, bar_width, label=label_printed)
+    
+        bar_positions = [pos + bar_width for pos in bar_positions]
+    
+    # Ajout des étiquettes, de la légende, etc.
+    ax.set_xlabel('Company')
+    ax.set_ylabel('Consent of mailing (%)')
+    ax.set_title(f'Consent of mailing for {type_of_activity}')
+    ax.set_xticks([pos + bar_width / 2 for pos in np.arange(len(categories))])
+    ax.set_xticklabels(categories)
+    ax.legend()
+    
+    plt.show()
+    save_file_s3("mailing_consent_", type_of_activity)
+
+
+def gender_bar(customer, type_of_activity):
+    company_genders = customer.groupby("number_company")[["gender_male", "gender_female", "gender_other"]].mean().reset_index()
+    
+    plt.bar(company_genders["number_company"], company_genders["gender_male"], label = "Homme")
+    plt.bar(company_genders["number_company"], company_genders["gender_female"], 
+            bottom = company_genders["gender_male"], label = "Femme")
+    plt.bar(company_genders["number_company"], company_genders["gender_other"], 
+            bottom = company_genders["gender_male"] + company_genders["gender_female"], label = "Inconnu")
+    
+    plt.xlabel('Company')
+    plt.ylabel("Gender")
+    plt.title(f"Gender of Customer for {type_of_activity}")
+    plt.legend()
+
+    plt.xticks(company_genders["number_company"], ["{}".format(i) for i in company_genders["number_company"]])
+ 
+    plt.show()
+    save_file_s3("gender_bar_", type_of_activity)
+
+
+def country_bar(customer, type_of_activity):
+    company_country_fr = customer.groupby("number_company")["country_fr"].mean().reset_index()
+    plt.bar(company_country_fr["number_company"], company_country_fr["country_fr"])
+    
+    plt.xlabel('Company')
+    plt.ylabel("Share of French Customer")
+    plt.title(f"Share of French Customer for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("country_bar_", type_of_activity)
+
+
+def lazy_customer_plot(campaigns_kpi, type_of_activity):
+    company_lazy_customers = campaigns_kpi.groupby("number_company")["no_campaign_opened"].mean().reset_index()
+    plt.bar(company_lazy_customers["number_company"], company_lazy_customers["no_campaign_opened"])
+    
+    plt.xlabel('Company')
+    plt.ylabel("Share of Customers who did not open mail")
+    plt.title(f"Share of Customers who did not open mail for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("lazy_customer_", type_of_activity)
+
+
+def campaigns_effectiveness(customer, type_of_activity):
+
+    customer["already_purchased"] = customer["purchase_count"]>0
+
+    nb_customers_purchasing = customer_sport[customer["already_purchased"]].groupby(["number_company","already_purchased"])["customer_id"].count().reset_index()
+    nb_customers_no_purchase = customer_sport[~customer["already_purchased"]].groupby(["number_company","already_purchased"])["customer_id"].count().reset_index()
+
+    plt.bar(nb_customers_purchasing["number_company"], nb_customers_purchasing["customer_id"]/1000, label = "has purchased")
+    plt.bar(nb_customers_no_purchase["number_company"], nb_customers_no_purchase["customer_id"]/1000, 
+            bottom = nb_customers_purchasing["customer_id"]/1000, label = "has not purchased")
+    
+    plt.xlabel('Company')
+    plt.ylabel("Number of Customers (thousands)")
+    plt.title(f"Number of Customers of have bought or have received mails for {type_of_activity}")
+    plt.legend()
+    plt.show()
+    save_file_s3("campaigns_effectiveness_", type_of_activity)
+
+
+def sale_dynamics(products, campaigns_brut, type_of_activity):
+    purchase_min = products.groupby(['customer_id'])['purchase_date'].min().reset_index()
+    purchase_min.rename(columns = {'purchase_date' : 'first_purchase_event'}, inplace = True)
+    purchase_min['first_purchase_event'] = pd.to_datetime(purchase_min['first_purchase_event'])
+    purchase_min['first_purchase_month'] = pd.to_datetime(purchase_min['first_purchase_event'].dt.strftime('%Y-%m'))
+
+    first_mail_received = campaigns_brut.groupby('customer_id')['sent_at'].min().reset_index()
+    first_mail_received.rename(columns = {'sent_at' : 'first_email_reception'}, inplace = True)
+    first_mail_received['first_email_reception'] = pd.to_datetime(first_mail_received['first_email_reception'])
+    first_mail_received['first_email_month'] = pd.to_datetime(first_mail_received['first_email_reception'].dt.strftime('%Y-%m'))
+
+    known_customer = pd.merge(purchase_min[['customer_id', 'first_purchase_month']], 
+                          first_mail_received[['customer_id', 'first_email_month']], on = 'customer_id', how = 'outer')
+
+    known_customer['known_date'] = pd.to_datetime(known_customer[['first_email_month', 'first_purchase_month']].min(axis = 1), utc = True, format = 'ISO8601')
+
+    purchases_count = pd.merge(products[['customer_id', 'purchase_id', 'purchase_date']].drop_duplicates(), known_customer[['customer_id', 'known_date']], on = ['customer_id'], how = 'inner')
+    purchases_count['is_customer_known'] = purchases_count['purchase_date'] > purchases_count['known_date'] + pd.DateOffset(months=1)
+    purchases_count['purchase_date_month'] = pd.to_datetime(purchases_count['purchase_date'].dt.strftime('%Y-%m'))
+    purchases_count = purchases_count[purchases_count['customer_id'] != 1]
+    
+    nb_purchases_graph = purchases_count.groupby(['purchase_date_month', 'is_customer_known'])['purchase_id'].count().reset_index()
+    nb_purchases_graph.rename(columns = {'purchase_id' : 'nb_purchases'}, inplace = True)
+    
+    nb_purchases_graph_2 = purchases_count.groupby(['purchase_date_month', 'is_customer_known'])['customer_id'].nunique().reset_index()
+    nb_purchases_graph_2.rename(columns = {'customer_id' : 'nb_new_customer'}, inplace = True)
+
+    purchases_graph = nb_purchases_graph
+    
+    purchases_graph_used = purchases_graph[purchases_graph["purchase_date_month"] >= datetime(2021,3,1)]
+    purchases_graph_used_0 = purchases_graph_used[purchases_graph_used["is_customer_known"]==False]
+    purchases_graph_used_1 = purchases_graph_used[purchases_graph_used["is_customer_known"]==True]
+    
+    plt.bar(purchases_graph_used_0["purchase_date_month"], purchases_graph_used_0["nb_purchases"], width=12, label = "Nouveau client")
+    plt.bar(purchases_graph_used_0["purchase_date_month"], purchases_graph_used_1["nb_purchases"], 
+            bottom = purchases_graph_used_0["nb_purchases"], width=12, label = "Ancien client")
+    
+    plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b%y'))
+    
+    plt.xlabel('Month')
+    plt.ylabel("Number of Sales")
+    plt.title(f"Number of Sales for {type_of_activity}")
+    plt.legend()
+    
+    plt.show()
+    save_file_s3("sale_dynamics_", type_of_activity)
+
+
+def tickets_internet(tickets, type_of_activity):
+    nb_tickets_internet = products_purchased_reduced_spectacle.groupby("number_company")[["nb_tickets", "nb_tickets_internet"]].sum().reset_index()
+    nb_tickets_internet["Share_ticket_internet"] = nb_tickets_internet["nb_tickets_internet"]*100 / nb_tickets_internet["nb_tickets"]
+
+    plt.bar(nb_tickets_internet["number_company"],  nb_tickets_internet["Share_ticket_internet"])
+    
+    plt.xlabel('Company')
+    plt.ylabel("Share of Tickets Bought Online")
+    plt.title(f"Share of Tickets Bought Online for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("tickets_internet_", type_of_activity)
+    
+
+def box_plot_price_tickets(tickets, type_of_activity):
+    price_tickets = tickets[(tickets['total_amount'] > 0)]
+    sns.boxplot(data=price_tickets, y="total_amount", x="number_company", showfliers=False, showmeans=True)
+    plt.title(f"Box plot of price tickets for {type_of_activity}")
+    
+    plt.show()
+    save_file_s3("box_plot_price_tickets_", type_of_activity)
+
+