update CA segment analysis

0_7_CA_segment.py

@@ -0,0 +1,77 @@
+# importations
+import pandas as pd
+from pandas import DataFrame
+import numpy as np
+import os
+import s3fs
+import re
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, recall_score
+from sklearn.utils import class_weight
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.model_selection import GridSearchCV
+from sklearn.preprocessing import StandardScaler, MaxAbsScaler, MinMaxScaler
+from sklearn.metrics import make_scorer, f1_score, balanced_accuracy_score
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.metrics import roc_curve, auc, precision_recall_curve, average_precision_score
+from sklearn.exceptions import ConvergenceWarning, DataConversionWarning
+from sklearn.naive_bayes import GaussianNB
+from scipy.optimize import fsolve
+import pickle
+import warnings
+
+# define type of activity 
+type_of_activity = "sport"
+PATH = f"projet-bdc2324-team1/Output_expected_CA/{type_of_activity}/"
+
+# comparison with bias of the train set - X train to be defined
+X_train_score = logit_cv.predict_proba(X_train)[:, 1]
+
+bias_train_set = find_bias(odd_ratios = odd_ratio(adjust_score_1(X_train_score)), 
+                           y_objective = y_train["y_has_purchased"].sum(),
+                           initial_guess=6)
+
+score_adjusted_train = adjusted_score(odd_ratio(adjust_score_1(X_test_segment["score"])), bias = bias_train_set)
+X_test_segment["score_adjusted"] = score_adjusted_train
+
+
+# plot adjusted scores and save (to be tested)
+plot_hist_scores(X_test_segment, score = "score", score_adjusted = "score_adjusted")
+
+image_buffer = io.BytesIO()
+    plt.savefig(image_buffer, format='png')
+    image_buffer.seek(0)
+    file_name = "hist_score_adjusted"
+    FILE_PATH_OUT_S3 = PATH + file_name + type_of_activity + ".png"
+    with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:
+        s3_file.write(image_buffer.read())
+    plt.close()
+
+# comparison between score and adjusted score
+X_test_table_adjusted_scores = X_test_segment.groupby("quartile")[["score","score_adjusted", "has_purchased"]].mean().reset_index().round(2)
+
+file_name = "table_adjusted_score"
+FILE_PATH_OUT_S3 = PATH + file_name +  type_of_activity + ".csv"
+with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
+    X_test_table_adjusted_scores.to_csv(file_out, index = False)
+
+
+# project revenue
+X_test_segment = project_tickets_CA (X_test_segment, "nb_tickets", "total_amount", "score_adjusted", duration_ref=1.5, duration_projection=1)
+
+
+# table summarizing projections
+X_test_expected_CA = round(summary_expected_CA(df=X_test_segment, segment="quartile", nb_tickets_expected="nb_tickets_expected", total_amount_expected="total_amount_expected", total_amount="total_amount"),2)
+
+file_name = "table_expected_CA"
+FILE_PATH_OUT_S3 = PATH + file_name +  type_of_activity + ".csv"
+with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
+    X_test_expected_CA.to_csv(file_out, index = False)
+
+

utils_CA_segment.py

@@ -1,7 +1,5 @@
 def odd_ratio(score) :
     """
-    Calculate the odd ratio from a score.
-
     Args:
     - score (Union[float, int]): Score value.
 
@@ -102,13 +100,15 @@ def project_tickets_CA (df, nb_tickets, total_amount, score_adjusted, duration_r
     duration_ratio = duration_ref/duration_projection
     """
 
+    duration_ratio = duration_ref/duration_projection
+
     df_output = df
 
-    df_output["nb_tickets_projected"] = df_output[nb_tickets] / duration_ratio
+    df_output.loc[:,"nb_tickets_projected"] = df_output.loc[:,nb_tickets] / duration_ratio
-    df_output["total_amount_projected"] = df_output[total_amount] / duration_ratio
+    df_output.loc[:,"total_amount_projected"] = df_output.loc[:,total_amount] / duration_ratio
     
-    df_output["nb_tickets_expected"] = df_output[score_adjusted] * df_output["nb_tickets_projected"]
+    df_output.loc[:,"nb_tickets_expected"] = df_output.loc[:,score_adjusted] * df_output.loc[:,"nb_tickets_projected"]
-    df_output["total_amount_expected"] = df_output[score_adjusted] * df_output["total_amount_projected"]
+    df_output.loc[:,"total_amount_expected"] = df_output.loc[:,score_adjusted] * df_output.loc[:,"total_amount_projected"]
 
     return df_output
     
@@ -138,8 +138,6 @@ def summary_expected_CA(df, segment, nb_tickets_expected, total_amount_expected,
     df_expected_CA.insert(2, "size_perct", 100 * df_expected_CA["size"]/df_expected_CA["size"].sum())
     
     # compute share of CA recovered
-    duration_ref=1.5
-    duration_projection=1
     duration_ratio=duration_ref/duration_projection
     
     df_expected_CA["perct_revenue_recovered"] = 100 * duration_ratio * df_expected_CA[total_amount_expected] / \