Upload __notebook_source__ (1).ipynb

src/__notebook_source__ (1).ipynb

@@ -0,0 +1,164 @@
+# This Python 3 environment comes with many helpful analytics libraries installed
+# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
+# For example, here's several helpful packages to load
+
+import numpy as np # linear algebra
+import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
+
+# Input data files are available in the read-only "../input/" directory
+# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory
+
+import os
+for dirname, _, filenames in os.walk('/kaggle/input'):
+    for filename in filenames:
+        print(os.path.join(dirname, filename))
+
+# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
+# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session
+
+
+
+
+
+
+
+
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import roc_auc_score, confusion_matrix, classification_report, RocCurveDisplay
+
+from sklearn.linear_model import LogisticRegression
+
+
+
+
+
+df = pd.read_csv("/kaggle/input/creditcardfraud/creditcard.csv")
+df.head()
+
+
+
+
+
+
+
+
+df.shape
+
+
+df.info()
+
+
+df.columns
+
+
+df.isnull().sum().sort_values(ascending=False)
+
+
+df["Class"].value_counts()
+
+
+sns.countplot(x="Class", data=df)
+plt.title("Class Distribution")
+plt.show()
+
+
+plt.figure(figsize=(8,4))
+sns.histplot(df["Amount"], bins=50)
+plt.title("Transaction Amount Distribution")
+plt.show()
+
+
+
+
+
+
+
+
+scaler = StandardScaler()
+
+df["Amount"] = scaler.fit_transform(df[["Amount"]])
+df["Time"] = scaler.fit_transform(df[["Time"]])
+
+
+
+
+
+X = df.drop("Class", axis=1)
+y = df["Class"]
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y, random_state=42)
+
+
+
+
+
+
+
+
+model = LogisticRegression(max_iter=1000)
+model.fit(X_train, y_train)
+
+
+
+
+
+
+
+
+y_pred_proba = model.predict_proba(X_test)[:, 1]
+roc_auc_score(y_test, y_pred_proba)
+
+
+
+
+
+RocCurveDisplay.from_predictions(y_test, y_pred_proba)
+plt.show()
+
+
+
+
+
+y_pred = model.predict(X_test)
+
+cm = confusion_matrix(y_test, y_pred)
+
+sns.heatmap(cm, annot=True, fmt="d", cmap="Blues")
+plt.title("Confusion Matrix")
+plt.show()
+
+
+
+
+
+print(classification_report(y_test, y_pred))
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+import joblib
+
+joblib.dump(model, "model.pkl")
+
+
+np.save("X_test.npy", X_test)
+np.save("y_test.npy", y_test)
+
+
+