Text Classification.ipynb

Kernel: Python 3 (ipykernel)

import nltk
nltk.download()

Text Classification with NLTK

Text Classification is the process of assigning a label or category to a given piece of text. For example, we can classify emails as spam or not spam, tweets as positive or negative, and articles as relevant or not relevant to a given topic.

Let us take an example:

• I am happy with your response

• We have a robbery reported on 20th July near Delhi

• I am not satisfied with your feedback

• I am ok with this situation

Example: Let us take and example of news classification, where we can train a model to predict the category of a news article based on its content. Here’s an example of how to do this using scikit-learn:

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
import pandas as pd

# Load the dataset
news = pd.read_csv('newss.csv')

news.head()

news.shape

(2445, 3)

news = news.dropna(how='any',axis=0)

news.describe(include="object")

# Split the data into training and testing sets
from sklearn.model_selection import train_test_split  
X_train, X_test, y_train, y_test = train_test_split(news['text'], news['category'], test_size=0.2)

# Create a TfidfVectorizer to convert text to numerical features
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(X_train)
X_test = vectorizer.transform(X_test)

# Train a logistic regression model
news_pred = LogisticRegression()
news_pred.fit(X_train, y_train)

# Evaluate the model on the test set
score = news_pred.score(X_test, y_test)
print('Accuracy:', score)

Accuracy: 0.901840490797546

y_pred=news_pred.predict(X_test)

# import the metrics class
from sklearn import metrics
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
cnf_matrix

array([[229,  20],
       [ 28, 212]], dtype=int64)

from sklearn.metrics import multilabel_confusion_matrix multilabel_confusion_matrix(y_test, y_pred,

                      labels=[0 ,1])

import seaborn as sns
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.pyplot import pie, axis, show
%matplotlib inline
import numpy as np
class_names=[0,1] # name  of classes
fig, ax = plt.subplots()
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
# create heatmap
sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')

# TF+TP/TF+TP+FP+FN

Text(0.5, 257.44, 'Predicted label')

## Model parameters study :
from sklearn import metrics
count_misclassified = (y_test != y_pred).sum()
print('Misclassified samples: {}'.format(count_misclassified))
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Misclassified samples: 48
Accuracy: 0.901840490797546

90% times we will be able to classify whether news is true or False

Checking the Model Performance on new data

# Sample data for testing
sample_data = [
    "This is a legitimate news article about recent scientific discoveries.",
    "Breaking: UFO spotted over New York City!",
    "Study finds that eating chocolate can improve memory.",
    "Breaking News: Famous celebrity announces presidential run.",
    "New research reveals the dangers of excessive screen time for children."
]


def news_pred_predict(sample_texts):
    # This function should take a list of text samples and return the predictions made by your model
    # Replace this with the code that uses your trained model to make predictions
    predictions = ['fake' if "Breaking" in text else 'true' for text in sample_texts]  # Placeholder prediction logic
    return predictions

# Test the model
predictions = news_pred_predict(sample_data)

# Print the predictions
for text, prediction in zip(sample_data, predictions):
    print("Text:", text)
    print("Prediction:", prediction)
    print()

Text: This is a legitimate news article about recent scientific discoveries.
Prediction: true

Text: Breaking: UFO spotted over New York City!
Prediction: fake

Text: Study finds that eating chocolate can improve memory.
Prediction: true

Text: Breaking News: Famous celebrity announces presidential run.
Prediction: fake

Text: New research reveals the dangers of excessive screen time for children.
Prediction: true