# Install necessary packages (if running in Colab)
!pip install seaborn
# Import required libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_breast_cancer
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
# Load built-in dataset
data = load_breast_cancer()
df = pd.DataFrame(data.data, columns=data.feature_names)
y = pd.Series(data.target)
# Check for missing values
print("Missing values:\n", df.isna().sum())
# Correlation matrix
plt.figure(figsize=(15, 11))
sns.heatmap(df.corr(), annot=False, cmap='coolwarm')
plt.title('Correlation Matrix')
plt.show()
# Feature scaling
scaler = StandardScaler()
X_scaled = scaler.fit_transform(df)
# Train-test split
x_train, x_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.27, random_state=42)
# Decision tree model
tree = DecisionTreeClassifier(random_state=42, criterion='entropy', max_depth=4)
tree.fit(x_train, y_train)
y_pred = tree.predict(x_test)
# Accuracy
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy * 100)
# Visualize decision tree
plt.figure(figsize=(12, 8))
plot_tree(tree, filled=True, class_names=data.target_names, feature_names=data.feature_names, rounded=True, fontsize=8)
plt.title('Decision Tree Visualization')
plt.show()
Requirement already satisfied: seaborn in /usr/local/lib/python3.11/dist-packages (0.13.2)
Requirement already satisfied: numpy!=1.24.0,>=1.20 in /usr/local/lib/python3.11/dist-packages (from seaborn) (2.0.2)
Requirement already satisfied: pandas>=1.2 in /usr/local/lib/python3.11/dist-packages (from seaborn) (2.2.2)
Requirement already satisfied: matplotlib!=3.6.1,>=3.4 in /usr/local/lib/python3.11/dist-packages (from seaborn) (3.10.0)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (0.12
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn)
Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (2
Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn) (11.1.0
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seaborn)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.11/dist-packages (from matplotlib!=3.6.1,>=3.4->seabor
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2->seaborn) (2025.2)
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2->seaborn) (2025.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.7->matplotlib!=3.6.1,>=3
Missing values:
mean radius 0
mean texture 0
mean perimeter 0
mean area 0
mean smoothness 0
mean compactness 0
mean concavity 0
mean concave points 0
mean symmetry 0
mean fractal dimension 0
radius error 0
texture error 0
perimeter error 0
area error 0
smoothness error 0
compactness error 0
concavity error 0
concave points error 0
symmetry error 0
fractal dimension error 0
worst radius 0
worst texture 0
worst perimeter 0
worst area 0
worst smoothness 0
worst compactness 0
worst concavity 0
worst concave points 0
worst symmetry 0
worst fractal dimension 0
dtype: int64
Accuracy: 96.1038961038961
