# -*- coding: utf-8 -*-
"""ML.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1N6R2R3PY04PitBN4M6QNX-tuBPdqglVz
"""

from google.colab import drive
drive.mount('/content/drive')

import pandas as pd

file_path = '/content/drive/My Drive/CIS 519 Final Project/Dataset/cleaned_headlines.csv'
df = pd.read_csv(file_path)
df

class_counts = df['outlet'].value_counts()
print(class_counts)

from sklearn.model_selection import train_test_split
X = df['title']
y = df['labels']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

from sklearn.feature_extraction.text import TfidfVectorizer
tfidf = TfidfVectorizer(max_features=5000, ngram_range=(1, 2), stop_words='english')
X_train_tfidf = tfidf.fit_transform(X_train)
X_test_tfidf = tfidf.transform(X_test)

"""# Logistic Regression"""

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, classification_report
model = LogisticRegression(max_iter=200)
model.fit(X_train_tfidf, y_train)
y_pred = model.predict(X_test_tfidf)
accuracy = accuracy_score(y_test, y_pred)
print(f"Logistic Regression Accuracy: {accuracy:.4f}")
print(classification_report(y_test, y_pred))

"""# Random Forest"""

from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=100, random_state=42)

model.fit(X_train_tfidf, y_train)
y_pred = model.predict(X_test_tfidf)
accuracy = accuracy_score(y_test, y_pred)
print(f"Random Forest Accuracy: {accuracy:.4f}")
print(classification_report(y_test, y_pred))

"""# Support Vector Machine"""

from sklearn.svm import SVC
svm_model = SVC(kernel='linear', random_state=42)
svm_model.fit(X_train_tfidf, y_train)
y_pred = svm_model.predict(X_test_tfidf)
accuracy = accuracy_score(y_test, y_pred)
print(f"Random Forest Accuracy: {accuracy:.4f}")
print(classification_report(y_test, y_pred))