IUM_05

.gitignore

@@ -2,3 +2,4 @@ creditcardfraud.zip
 creditcard.csv
 data
 model/model.keras
+stats_data

create-dataset.py

@@ -1,9 +1,6 @@
 import os
 import pandas as pd
-import numpy as np
-
 from sklearn.preprocessing import StandardScaler
-
 from sklearn.model_selection import train_test_split
 
 
@@ -18,72 +15,27 @@ def normalize_data(df):
     return df
 
 
-def create_undersample_data(df):
+def split_data(df):
-    # Determine the number of instances in the minority class
-    fraud_count = len(df[df.Class == 1])
-    fraud_indices = np.array(df[df.Class == 1].index)
-
-    # Select indices corresponding to majority class instances
-    normal_indices = df[df.Class == 0].index
-
-    # Randomly sample the same number of instances from the majority class
-    random_normal_indices = np.random.choice(normal_indices, fraud_count, replace=False)
-    random_normal_indices = np.array(random_normal_indices)
-
-    # Combine indices of both classes
-    undersample_indice = np.concatenate([fraud_indices, random_normal_indices])
-
-    # Undersample dataset
-    undersample_data = df.iloc[undersample_indice, :]
-
-    X_undersample = undersample_data.iloc[:, undersample_data.columns != "Class"]
-    y_undersample = undersample_data.iloc[:, undersample_data.columns == "Class"]
-
-    return undersample_data, X_undersample, y_undersample
-
-
-def split_undersample_data(X_undersample, y_undersample):
-    X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = (
-        train_test_split(X_undersample, y_undersample, test_size=0.3, random_state=0)
-    )
-
-    return (
-        X_train_undersample,
-        X_test_undersample,
-        y_train_undersample,
-        y_test_undersample,
-    )
-
-
-def save_undersample_data(
-    undersample_data,
-    X_train_undersample,
-    X_test_undersample,
-    y_train_undersample,
-    y_test_undersample,
-):
-    undersample_data.to_csv("data/undersample_data.csv", index=False)
-    X_train_undersample.to_csv("data/X_train_undersample.csv", index=False)
-    X_test_undersample.to_csv("data/X_test_undersample.csv", index=False)
-    y_train_undersample.to_csv("data/y_train_undersample.csv", index=False)
-    y_test_undersample.to_csv("data/y_test_undersample.csv", index=False)
-
-
-def split_whole_data(df):
     X = df.iloc[:, df.columns != "Class"]
     y = df.iloc[:, df.columns == "Class"]
 
     X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.3, random_state=0
+        X, y, test_size=0.2, random_state=0
     )
-    return X_train, X_test, y_train, y_test
+    X_train, X_val, y_train, y_val = train_test_split(
+        X_train, y_train, test_size=0.25, random_state=0
+    )
+
+    return X_train, X_val, X_test, y_train, y_val, y_test
 
 
-def save_whole_data(df, X_train, X_test, y_train, y_test):
+def save_data(df, X_train, X_val, X_test, y_train, y_val, y_test):
     df.to_csv("data/creditcard.csv", index=False)
     X_train.to_csv("data/X_train.csv", index=False)
+    X_val.to_csv("data/X_val.csv", index=False)
     X_test.to_csv("data/X_test.csv", index=False)
     y_train.to_csv("data/y_train.csv", index=False)
+    y_val.to_csv("data/y_val.csv", index=False)
     y_test.to_csv("data/y_test.csv", index=False)
 
 
@@ -94,20 +46,8 @@ def main():
     df = load_data("creditcard.csv")
     df = normalize_data(df)
 
-    undersample_data, X_undersample, y_undersample = create_undersample_data(df)
+    X_train, X_val, X_test, y_train, y_val, y_test = split_data(df)
-    X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample = (
+    save_data(df, X_train, X_val, X_test, y_train, y_val, y_test)
-        split_undersample_data(X_undersample, y_undersample)
-    )
-    save_undersample_data(
-        undersample_data,
-        X_train_undersample,
-        X_test_undersample,
-        y_train_undersample,
-        y_test_undersample,
-    )
-
-    X_train, X_test, y_train, y_test = split_whole_data(df)
-    save_whole_data(df, X_train, X_test, y_train, y_test)
 
 
 if __name__ == "__main__":

dataset-stats.py

@@ -7,16 +7,12 @@ def write_to_file(file_name):
     df = pd.read_csv("data/creditcard.csv")
     pd.set_option("display.max_columns", None)
 
-    undersample_data = pd.read_csv("data/undersample_data.csv")
-    X_test_undersample = pd.read_csv("data/X_test_undersample.csv")
-    y_test_undersample = pd.read_csv("data/y_test_undersample.csv")
-    X_train_undersample = pd.read_csv("data/X_train_undersample.csv")
-    y_train_undersample = pd.read_csv("data/y_train_undersample.csv")
-
-    X_test = pd.read_csv("data/X_test.csv")
-    y_test = pd.read_csv("data/y_test.csv")
     X_train = pd.read_csv("data/X_train.csv")
+    X_val = pd.read_csv("data/X_val.csv")
+    X_test = pd.read_csv("data/X_test.csv")
     y_train = pd.read_csv("data/y_train.csv")
+    y_val = pd.read_csv("data/y_val.csv")
+    y_test = pd.read_csv("data/y_test.csv")
 
     with open("stats_data/" + file_name, "w") as f:
         sys.stdout = f
@@ -41,24 +37,7 @@ def write_to_file(file_name):
 
         f.write("\n\n")
 
-        f.write("Size of undersampled dataset\n")
+        f.write("Statistical measures of the training dataset\n")
-        undersample_data.info()
-
-        f.write("\n\n")
-
-        f.write("Summary statistics of the undersampled dataset\n")
-        f.write(str(undersample_data.describe()))
-
-        f.write("\n\n")
-
-        f.write(
-            "Distribution of legitimate and fraudulent transactions in an undersampled dataset\n"
-        )
-        f.write(str(undersample_data["Class"].value_counts()))
-
-        f.write("\n\n")
-
-        f.write("Statistical measures of the training dataset of whole data\n")
         pd.concat([X_train, y_train], axis=1).info()
         f.write("\n")
         f.write(str(pd.concat([X_train, y_train], axis=1).describe()))
@@ -67,49 +46,22 @@ def write_to_file(file_name):
 
         f.write("\n\n")
 
-        f.write("Statistical measures of the test dataset of whole data\n")
+        f.write("Statistical measures of the validation dataset\n")
+        pd.concat([X_val, y_val], axis=1).info()
+        f.write("\n")
+        f.write(str(pd.concat([X_val, y_val], axis=1).describe()))
+        f.write("\n")
+        f.write(str(pd.concat([X_val, y_val], axis=1)["Class"].value_counts()))
+
+        f.write("\n\n")
+
+        f.write("Statistical measures of the test dataset\n")
         pd.concat([X_test, y_test], axis=1).info()
         f.write("\n")
         f.write(str(pd.concat([X_test, y_test], axis=1).describe()))
         f.write("\n")
         f.write(str(pd.concat([X_test, y_test], axis=1)["Class"].value_counts()))
 
-        f.write("\n\n")
-
-        f.write("Statistical measures of the training dataset of undersampled data\n")
-        pd.concat([X_train_undersample, y_train_undersample], axis=1).info()
-        f.write("\n")
-        f.write(
-            str(
-                pd.concat([X_train_undersample, y_train_undersample], axis=1).describe()
-            )
-        )
-        f.write("\n")
-        f.write(
-            str(
-                pd.concat([X_train_undersample, y_train_undersample], axis=1)[
-                    "Class"
-                ].value_counts()
-            )
-        )
-
-        f.write("\n\n")
-
-        f.write("Statistical measures of the test dataset of undersampled data\n")
-        pd.concat([X_test_undersample, y_test_undersample], axis=1).info()
-        f.write("\n")
-        f.write(
-            str(pd.concat([X_test_undersample, y_test_undersample], axis=1).describe())
-        )
-        f.write("\n")
-        f.write(
-            str(
-                pd.concat([X_test_undersample, y_test_undersample], axis=1)[
-                    "Class"
-                ].value_counts()
-            )
-        )
-
         sys.stdout = sys.__stdout__
 
 

train_model.py

@@ -10,12 +10,17 @@ import pandas as pd
 
 def main():
     X_train = pd.read_csv("data/X_train.csv")
+    X_val = pd.read_csv("data/X_val.csv")
     y_train = pd.read_csv("data/y_train.csv")
+    y_val = pd.read_csv("data/y_val.csv")
 
     X_train = X_train.to_numpy()
+    X_val = X_val.to_numpy()
     y_train = y_train.to_numpy()
+    y_val = y_val.to_numpy()
 
     X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
+    X_val = X_val.reshape(X_val.shape[0], X_val.shape[1], 1)
 
     model = Sequential(
         [
@@ -41,6 +46,7 @@ def main():
     model.fit(
         X_train,
         y_train,
+        validation_data=(X_val, y_val),
         epochs=5,
         verbose=1,
     )