15/09/2023, 15:44 E21CSEU0962_Lab4.

ipynb - Colaboratory

1
2 from sklearn.datasets import load_iris
3 from sklearn.tree import DecisionTreeClassifier
4 from sklearn.model_selection import cross_val_score, GridSearchCV
5 import pandas as pd
6 import matplotlib.pyplot as plt
7 from sklearn import tree
8
9

1 iris = load_iris()
2
3 df = pd.DataFrame(data=iris.data, columns=iris.feature_names)
4 df['target'] = iris.target
5 clf = DecisionTreeClassifier()

1 scores = cross_val_score(clf, df.drop('target', axis=1), df['target'], cv=5)

2
3 print("Cross-validation scores:", scores)
4 print("Mean accuracy:", scores.mean())

Cross-validation scores: [0.96666667 0.96666667 0.9 1. 1. ]

Mean accuracy: 0.9666666666666668

1 clf.fit(df.drop('target', axis=1), df['target'])

2
3 plt.figure(figsize=(12,10))
4 tree.plot_tree(clf, feature_names=iris.feature_names, class_names=iris.target_names, filled=True)
5 plt.show()

1
2 param_grid = {
3 'max_depth': [2, 4, 6, 8],
4 'min_samples_split': [2, 4, 6, 8],
5 'min_samples_leaf': [1, 2, 3]

https://colab.research.google.com/drive/18ZAzdOE2FZtW5RKLs5wsWGw5syPidvh-#printMode=true 1/4
15/09/2023, 15:44 E21CSEU0962_Lab4.ipynb - Colaboratory
6 }
7

1
2 grid_search = GridSearchCV(DecisionTreeClassifier(), param_grid, cv=5, scoring='accuracy')
3 grid_search.fit(df.drop('target', axis=1), df['target'])
4
5 best_params = grid_search.best_params_
6 best_score = grid_search.best_score_
7
8 print("Best Hyperparameters:", best_params)
9 print("Best Score (Accuracy):", best_score)

Best Hyperparameters: {'max_depth': 4, 'min_samples_leaf': 1, 'min_samples_split': 4}

Best Score (Accuracy): 0.9666666666666668

q2

1 import pandas as pd
2
3 df = pd.read_csv('creditcard.csv')
4
5 print("Dataset Shape:", df.shape)
6 print("Statistical Summary:")
7 print(df.describe())
8

Dataset Shape: (284807, 31)

Statistical Summary:
Time V1 V2 V3 V4 \
count 284807.000000 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05
mean 94813.859575 1.168375e-15 3.416908e-16 -1.379537e-15 2.074095e-15
std 47488.145955 1.958696e+00 1.651309e+00 1.516255e+00 1.415869e+00
min 0.000000 -5.640751e+01 -7.271573e+01 -4.832559e+01 -5.683171e+00
25% 54201.500000 -9.203734e-01 -5.985499e-01 -8.903648e-01 -8.486401e-01
50% 84692.000000 1.810880e-02 6.548556e-02 1.798463e-01 -1.984653e-02
75% 139320.500000 1.315642e+00 8.037239e-01 1.027196e+00 7.433413e-01
max 172792.000000 2.454930e+00 2.205773e+01 9.382558e+00 1.687534e+01

V5 V6 V7 V8 V9 \
count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05
mean 9.604066e-16 1.487313e-15 -5.556467e-16 1.213481e-16 -2.406331e-15
std 1.380247e+00 1.332271e+00 1.237094e+00 1.194353e+00 1.098632e+00
min -1.137433e+02 -2.616051e+01 -4.355724e+01 -7.321672e+01 -1.343407e+01
25% -6.915971e-01 -7.682956e-01 -5.540759e-01 -2.086297e-01 -6.430976e-01
50% -5.433583e-02 -2.741871e-01 4.010308e-02 2.235804e-02 -5.142873e-02
75% 6.119264e-01 3.985649e-01 5.704361e-01 3.273459e-01 5.971390e-01
max 3.480167e+01 7.330163e+01 1.205895e+02 2.000721e+01 1.559499e+01

... V21 V22 V23 V24 \

count ... 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05
mean ... 1.654067e-16 -3.568593e-16 2.578648e-16 4.473266e-15
std ... 7.345240e-01 7.257016e-01 6.244603e-01 6.056471e-01
min ... -3.483038e+01 -1.093314e+01 -4.480774e+01 -2.836627e+00
25% ... -2.283949e-01 -5.423504e-01 -1.618463e-01 -3.545861e-01
50% ... -2.945017e-02 6.781943e-03 -1.119293e-02 4.097606e-02
75% ... 1.863772e-01 5.285536e-01 1.476421e-01 4.395266e-01
max ... 2.720284e+01 1.050309e+01 2.252841e+01 4.584549e+00

V25 V26 V27 V28 Amount \

count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 284807.000000
mean 5.340915e-16 1.683437e-15 -3.660091e-16 -1.227390e-16 88.349619
std 5.212781e-01 4.822270e-01 4.036325e-01 3.300833e-01 250.120109
min -1.029540e+01 -2.604551e+00 -2.256568e+01 -1.543008e+01 0.000000
25% -3.171451e-01 -3.269839e-01 -7.083953e-02 -5.295979e-02 5.600000
50% 1.659350e-02 -5.213911e-02 1.342146e-03 1.124383e-02 22.000000
75% 3.507156e-01 2.409522e-01 9.104512e-02 7.827995e-02 77.165000
max 7.519589e+00 3.517346e+00 3.161220e+01 3.384781e+01 25691.160000

Class
count 284807.000000
mean 0.001727
std 0.041527
min 0.000000
25% 0.000000
50% 0.000000
75% 0.000000
max 1.000000

[8 rows x 31 columns]

1 X = df.drop('Class', axis=1)
2 y = df['Class']
3
4 print("Features Shape (X):", X.shape)

https://colab.research.google.com/drive/18ZAzdOE2FZtW5RKLs5wsWGw5syPidvh-#printMode=true 2/4
15/09/2023, 15:44 E21CSEU0962_Lab4.ipynb - Colaboratory
5 print("Target Shape (y):", y.shape)
6
Features Shape (X): (284807, 30)
Target Shape (y): (284807,)

1 import seaborn as sns

2 import matplotlib.pyplot as plt
3
4 sns.countplot(x='Class', data=df)
5 plt.title('Distribution of Target Variable')
6 plt.show()
7

1 from sklearn.tree import DecisionTreeClassifier

2
3 dt_model = DecisionTreeClassifier()

1 from sklearn.model_selection import RepeatedStratifiedKFold

2
3 rkf = RepeatedStratifiedKFold(n_splits=10, n_repeats=1, random_state=1)

1 from sklearn.model_selection import cross_val_score

2 from sklearn.metrics import roc_auc_score
3
4 roc_auc_scores = cross_val_score(dt_model, X, y, cv=rkf, scoring='roc_auc')
5 print("ROC-AUC Scores:", roc_auc_scores)
6 print("Mean ROC-AUC:", roc_auc_scores.mean())
7

ROC-AUC Scores: [0.87728723 0.85693183 0.89766022 0.88736821 0.88747373 0.8797362

0.91970103 0.8467805 0.8568263 0.87735757]
Mean ROC-AUC: 0.8787122830612331

1
2 dt_model_balanced = DecisionTreeClassifier(class_weight="balanced")
3
4 roc_auc_scores_balanced = cross_val_score(dt_model_balanced, X, y, cv=rkf, scoring='roc_auc')
5 print("Balanced Class ROC-AUC Scores:", roc_auc_scores_balanced)
6 print("Mean ROC-AUC (Balanced Class):", roc_auc_scores_balanced.mean())
7

Balanced Class ROC-AUC Scores: [0.87726965 0.84671016 0.8976954 0.86718867 0.86725901 0.85985931
0.91980655 0.85700217 0.87741033 0.89766021]
Mean ROC-AUC (Balanced Class): 0.8767861446135539

https://colab.research.google.com/drive/18ZAzdOE2FZtW5RKLs5wsWGw5syPidvh-#printMode=true 3/4
15/09/2023, 15:44 E21CSEU0962_Lab4.ipynb - Colaboratory

https://colab.research.google.com/drive/18ZAzdOE2FZtW5RKLs5wsWGw5syPidvh-#printMode=true 4/4