import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Step 1.1: Convert dictionary to DataFrame
data = {
    'Feature1': [1, 2, np.nan, 4, 5],
    'Feature2': [5, np.nan, np.nan, 8, 9]
}

df = pd.DataFrame(data)


df['Feature1'].fillna(df['Feature1'].mean(), inplace=True)

# Step 1.4: Fill missing values in 'Feature2' with median
df['Feature2'].fillna(df['Feature2'].median(), inplace=True)





df['Target'] = [0, 1, 0, 1, 0]  # Example target values for classification


X = df.drop(columns=['Target'])  # Features (without 'Target')
y = df['Target']  # Target variable

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Step 3: Load Decision Tree Classifier
clf = DecisionTreeClassifier(random_state=42)

# Step 4: Train the model
clf.fit(X_train, y_train)

# Step 5: Make predictions
y_pred = clf.predict(X_test)

# Step 6: Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
print(f"\nDecision Tree Classifier Accuracy: {accuracy * 100:.2f}%")