yitingliii
commited on
Upload ml.py
Browse files
ml.py
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
+
"""ML.ipynb
|
3 |
+
|
4 |
+
Automatically generated by Colab.
|
5 |
+
|
6 |
+
Original file is located at
|
7 |
+
https://colab.research.google.com/drive/1N6R2R3PY04PitBN4M6QNX-tuBPdqglVz
|
8 |
+
"""
|
9 |
+
|
10 |
+
from google.colab import drive
|
11 |
+
drive.mount('/content/drive')
|
12 |
+
|
13 |
+
import pandas as pd
|
14 |
+
|
15 |
+
file_path = '/content/drive/My Drive/CIS 519 Final Project/Dataset/cleaned_headlines.csv'
|
16 |
+
df = pd.read_csv(file_path)
|
17 |
+
df
|
18 |
+
|
19 |
+
class_counts = df['outlet'].value_counts()
|
20 |
+
print(class_counts)
|
21 |
+
|
22 |
+
from sklearn.model_selection import train_test_split
|
23 |
+
X = df['title']
|
24 |
+
y = df['labels']
|
25 |
+
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
26 |
+
|
27 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
28 |
+
tfidf = TfidfVectorizer(max_features=5000, ngram_range=(1, 2), stop_words='english')
|
29 |
+
X_train_tfidf = tfidf.fit_transform(X_train)
|
30 |
+
X_test_tfidf = tfidf.transform(X_test)
|
31 |
+
|
32 |
+
"""# Logistic Regression"""
|
33 |
+
|
34 |
+
from sklearn.linear_model import LogisticRegression
|
35 |
+
from sklearn.metrics import accuracy_score, classification_report
|
36 |
+
model = LogisticRegression(max_iter=200)
|
37 |
+
model.fit(X_train_tfidf, y_train)
|
38 |
+
y_pred = model.predict(X_test_tfidf)
|
39 |
+
accuracy = accuracy_score(y_test, y_pred)
|
40 |
+
print(f"Logistic Regression Accuracy: {accuracy:.4f}")
|
41 |
+
print(classification_report(y_test, y_pred))
|
42 |
+
|
43 |
+
"""# Random Forest"""
|
44 |
+
|
45 |
+
from sklearn.ensemble import RandomForestClassifier
|
46 |
+
model = RandomForestClassifier(n_estimators=100, random_state=42)
|
47 |
+
|
48 |
+
model.fit(X_train_tfidf, y_train)
|
49 |
+
y_pred = model.predict(X_test_tfidf)
|
50 |
+
accuracy = accuracy_score(y_test, y_pred)
|
51 |
+
print(f"Random Forest Accuracy: {accuracy:.4f}")
|
52 |
+
print(classification_report(y_test, y_pred))
|
53 |
+
|
54 |
+
"""# Support Vector Machine"""
|
55 |
+
|
56 |
+
from sklearn.svm import SVC
|
57 |
+
svm_model = SVC(kernel='linear', random_state=42)
|
58 |
+
svm_model.fit(X_train_tfidf, y_train)
|
59 |
+
y_pred = svm_model.predict(X_test_tfidf)
|
60 |
+
accuracy = accuracy_score(y_test, y_pred)
|
61 |
+
print(f"Random Forest Accuracy: {accuracy:.4f}")
|
62 |
+
print(classification_report(y_test, y_pred))
|
63 |
+
|