# 1. Data Loading and Initial Exploration
# Import necessary libraries
import pandas as pd
# Load the dataset
file_path = "bank.csv"
df = pd.read_csv(file_path, delimiter=";")
# Display first few rows
print("\nFirst 5 Rows of the Dataset:")
df.head()

First 5 Rows of the Dataset:

	age	job	marital	education	default	balance	housing	loan	contact	day	month	duration	campaign	pdays	previous	poutcome	y
0	30	unemployed	married	primary	no	1787	no	no	cellular	19	oct	79	1	-1	0	unknown	no
1	33	services	married	secondary	no	4789	yes	yes	cellular	11	may	220	1	339	4	failure	no
2	35	management	single	tertiary	no	1350	yes	no	cellular	16	apr	185	1	330	1	failure	no
3	30	management	married	tertiary	no	1476	yes	yes	unknown	3	jun	199	4	-1	0	unknown	no
4	59	blue-collar	married	secondary	no	0	yes	no	unknown	5	may	226	1	-1	0	unknown	no

# Convert target variable 'y' to binary (0 for 'no', 1 for 'yes')
df['y'] = df['y'].map({'no': 0, 'yes': 1})
# Check unique values in the target column
print("\nUnique values in target variable (y):")
print(df['y'].value_counts())

Unique values in target variable (y):
y
0    4000
1     521
Name: count, dtype: int64

# Step 2: Encode Categorical Variables
# Identify categorical columns
categorical_cols = ['job', 'marital', 'education', 'default', 'housing', 'loan', 'contact', 'month', 'poutcome']

# Apply one-hot encoding
df_encoded = pd.get_dummies(df, columns=categorical_cols, drop_first=True)

# Display the new structure of the dataset
print("\nDataset after encoding categorical variables:")
df_encoded.head()

Dataset after encoding categorical variables:

	age	balance	day	duration	campaign	pdays	previous	y	job_blue-collar	job_entrepreneur	...	month_jul	month_jun	month_mar	month_may	month_nov	month_oct	month_sep	poutcome_other	poutcome_success	poutcome_unknown
0	30	1787	19	79	1	-1	0	0	False	False	...	False	False	False	False	False	True	False	False	False	True
1	33	4789	11	220	1	339	4	0	False	False	...	False	False	False	True	False	False	False	False	False	False
2	35	1350	16	185	1	330	1	0	False	False	...	False	False	False	False	False	False	False	False	False	False
3	30	1476	3	199	4	-1	0	0	False	False	...	False	True	False	False	False	False	False	False	False	True
4	59	0	5	226	1	-1	0	0	True	False	...	False	False	False	True	False	False	False	False	False	True

5 rows × 43 columns

# Step 3: Separate Features and Target Variable
# Separate features and target variable
X = df_encoded.drop(columns=['y'])
y = df_encoded['y']

# Display shape of feature matrix and target vector
print("\nShape of Features (X):", X.shape)
print("Shape of Target (y):", y.shape)

Shape of Features (X): (4521, 42)
Shape of Target (y): (4521,)

# Step 4: Feature Scaling
from sklearn.preprocessing import StandardScaler

# Initialize the StandardScaler
scaler = StandardScaler()

# Apply scaling to features
X_scaled = scaler.fit_transform(X)

# Convert back to DataFrame for better understanding
X_scaled_df = pd.DataFrame(X_scaled, columns=X.columns)

# Display first 5 rows of scaled data
print("\nFirst 5 rows after feature scaling:")
X_scaled_df.head()

First 5 rows after feature scaling:

	age	balance	day	duration	campaign	pdays	previous	job_blue-collar	job_entrepreneur	job_housemaid	...	month_jul	month_jun	month_mar	month_may	month_nov	month_oct	month_sep	poutcome_other	poutcome_success	poutcome_unknown
0	-1.056270	0.121072	0.374052	-0.711861	-0.576829	-0.407218	-0.320413	-0.514408	-0.196454	-0.159382	...	-0.430185	-0.364805	-0.104676	-0.669064	-0.306828	7.450671	-0.107869	-0.213447	-0.171381	0.469300
1	-0.772583	1.118644	-0.596026	-0.169194	-0.576829	2.989044	2.041734	-0.514408	-0.196454	-0.159382	...	-0.430185	-0.364805	-0.104676	1.494626	-0.306828	-0.134216	-0.107869	-0.213447	-0.171381	-2.130831
2	-0.583458	-0.024144	0.010273	-0.303898	-0.576829	2.899143	0.270124	-0.514408	-0.196454	-0.159382	...	-0.430185	-0.364805	-0.104676	-0.669064	-0.306828	-0.134216	-0.107869	-0.213447	-0.171381	-2.130831
3	-1.056270	0.017726	-1.566105	-0.250017	0.387967	-0.407218	-0.320413	-0.514408	-0.196454	-0.159382	...	-0.430185	2.741190	-0.104676	-0.669064	-0.306828	-0.134216	-0.107869	-0.213447	-0.171381	0.469300
4	1.686036	-0.472753	-1.323585	-0.146102	-0.576829	-0.407218	-0.320413	1.943983	-0.196454	-0.159382	...	-0.430185	-0.364805	-0.104676	1.494626	-0.306828	-0.134216	-0.107869	-0.213447	-0.171381	0.469300

5 rows × 42 columns

# Step 5: Split Data into Training and Testing Sets
from sklearn.model_selection import train_test_split

# Split the dataset (80% training, 20% testing)
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Display dataset sizes
print("\nTraining set size:", X_train.shape)
print("Testing set size:", X_test.shape)

Training set size: (3616, 42)
Testing set size: (905, 42)

# Step 6: Train Logistic Regression Model
from sklearn.linear_model import LogisticRegression

# Initialize and train the logistic regression model
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)

LogisticRegression(max_iter=1000)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

# Step 7: Make Predictions
# Predict on test data
y_pred = model.predict(X_test)

# Display first 10 predictions vs actual values
print("\nFirst 10 Actual vs Predicted Values:")
print(pd.DataFrame({'Actual': y_test[:10].values, 'Predicted': y_pred[:10]}))

First 10 Actual vs Predicted Values:
   Actual  Predicted
0       0          0
1       0          0
2       0          0
3       0          0
4       0          0
5       0          0
6       0          0
7       0          0
8       0          0
9       0          0

# Step 8: Evaluate the Model
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)

# Compute confusion matrix
conf_matrix = confusion_matrix(y_test, y_pred)

# Generate classification report
class_report = classification_report(y_test, y_pred)

# Display evaluation metrics
print("\nModel Accuracy:", accuracy)
print("\nConfusion Matrix:\n", conf_matrix)
print("\nClassification Report:\n", class_report)

Model Accuracy: 0.901657458563536

Confusion Matrix:
 [[789  18]
 [ 71  27]]

Classification Report:
               precision    recall  f1-score   support

           0       0.92      0.98      0.95       807
           1       0.60      0.28      0.38        98

    accuracy                           0.90       905
   macro avg       0.76      0.63      0.66       905
weighted avg       0.88      0.90      0.88       905

# Step 9: Visualize the Results
import matplotlib.pyplot as plt
import seaborn as sns

# Plot Confusion Matrix
plt.figure(figsize=(6, 4))
sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['No', 'Yes'], yticklabels=['No', 'Yes'])
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.title('Confusion Matrix')
plt.show()

# ROC Curve
from sklearn.metrics import roc_curve, auc

# Get probability scores
y_prob = model.predict_proba(X_test)[:,1]

# Compute ROC curve
fpr, tpr, _ = roc_curve(y_test, y_prob)
roc_auc = auc(fpr, tpr)

# Plot ROC Curve
plt.figure(figsize=(6, 4))
plt.plot(fpr, tpr, color='blue', label=f'ROC Curve (area = {roc_auc:.2f})')
plt.plot([0, 1], [0, 1], color='gray', linestyle='--')
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic (ROC) Curve')
plt.legend(loc='lower right')
plt.show()

# Step 10: Plot Actual vs Predicted Values
# Scatter plot for actual vs predicted values
plt.figure(figsize=(10,5))
plt.scatter(range(len(y_test)), y_test, color='blue', label='Actual', alpha=0.6)
plt.scatter(range(len(y_pred)), y_pred, color='red', label='Predicted', alpha=0.6, marker='x')

plt.xlabel('Sample Index')
plt.ylabel('Class (0 = No, 1 = Yes)')
plt.title('Actual vs Predicted Values')
plt.legend()
plt.show()