Amazing-Python-Scripts

1
import pandas as pd
2
import numpy as np
3
from sklearn.feature_extraction.text import TfidfVectorizer
4
from sklearn.model_selection import train_test_split
5
from sklearn.svm import SVC
6
from sklearn.metrics import accuracy_score, classification_report
7

8

9
def sentiment_analysis():
10
    """
11
    Perform sentiment analysis using an SVM classifier.
12

13
    The function reads the data from a CSV file, preprocesses it, and trains an SVM classifier
14
    for sentiment analysis on the 'text' column with the 'label' column as the target.
15

16
    Prints the accuracy and classification report on the test data.
17
    """
18
    # Load data from a CSV file (replace 'data.csv' with your data file)
19
    data = pd.read_csv('data.csv')
20

21
    # Preprocess data (remove any special characters, convert to lowercase, etc.)
22
    data['text'] = data['text'].apply(preprocess_text)
23

24
    # Split the data into features (X) and labels (y)
25
    X = data['text']
26
    y = data['label']
27

28
    # Convert text data to numerical features using TF-IDF
29
    vectorizer = TfidfVectorizer()
30
    X = vectorizer.fit_transform(X)
31

32
    # Split the data into training and testing sets
33
    X_train, X_test, y_train, y_test = train_test_split(
34
        X, y, test_size=0.2, random_state=42)
35

36
    # Train an SVM classifier
37
    svm_classifier = SVC(kernel='linear')
38
    svm_classifier.fit(X_train, y_train)
39

40
    # Make predictions on the test set
41
    y_pred = svm_classifier.predict(X_test)
42

43
    # Calculate and print accuracy and classification report
44
    accuracy = accuracy_score(y_test, y_pred)
45
    print("Accuracy:", accuracy)
46
    print("Classification Report:")
47
    print(classification_report(y_test, y_pred, zero_division=1))
48

49

50
def preprocess_text(text):
51
    # Replace special characters with spaces
52
    text = text.replace('\n', ' ')
53
    text = text.replace('\t', ' ')
54
    text = text.replace('-', ' ')
55

56
    # Convert to lowercase
57
    text = text.lower()
58

59
    return text
60

61

62
if __name__ == '__main__':
63
    sentiment_analysis()
64