from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.model_selection import train_test_split
# from sklearn.metrics import plot_confusion_matrix
features = ['Percent of adults with less than a high school diploma',
'Percent of adults with a high school diploma only',
'Percent of adults completing some college or associate\'s degree',
'Percent of adults with a bachelor\'s degree or higher', 'Poverty_rate', 'PopulationWhite', 'PopulationBlack',
'PopulationAmerican Indian/Alaska Native',
'PopulationAsian or Pacific Islander', 'PopulationNon-Hispanic',
'PopulationHispanic', 'PopulationMale', 'PopulationFemale']
X = df[features]
y = df['party']
# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
#train model
model = LogisticRegression(max_iter=1000)
model.fit(X_train, y_train)
#evaluate model
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
conf_matrix = confusion_matrix(y_test, y_pred, labels=df['party'].unique())
print(f"Accuracy: {accuracy:.2f}")
print("Confusion Matrix:")
print(conf_matrix)
import seaborn as sns
import matplotlib.pyplot as plt
#plot confusion matrix
plt.figure(figsize=(10, 8))
sns.set(font_scale=1.4)
# Plot using seaborn
sns.heatmap(conf_matrix, annot=True, fmt="d", annot_kws={"size": 16}, cmap='Blues',
xticklabels=df['party'].unique(), yticklabels=df['party'].unique()) # Font size
plt.xlabel('Predicted Labels', fontsize=18)
plt.ylabel('True Labels', fontsize=18)
plt.title('Confusion Matrix', fontsize=20)
plt.show()
