Update app.py

app.py

@@ -1,3 +1,6 @@
+import warnings
+warnings.filterwarnings('ignore')
+warnings.simplefilter('ignore')
 from sklearn.metrics import confusion_matrix
 from transformers import pipeline
 import numpy as np
@@ -19,31 +22,68 @@ import gradio as gr
 # pip install --upgrade transformers// update it if you get error
 # !pip install gradio // download it
 # Fetch the 20 newsgroups dataset
-import warnings
-warnings.filterwarnings('ignore')
-warnings.simplefilter('ignore')
-data = fetch_20newsgroups(subset='all', remove=('headers', 'footers', 'quotes'))
 
+data = fetch_20newsgroups(subset='all',remove=('headers', 'footers', 'quotes'))
+print("First few rows of the dataset:")
+print(data.data[:2])
 # Display information about the dataset
 print("Number of samples:", len(data.data))
-print("Target names:", data.target_names)
+print("\nTarget names:", data.target_names)
 # Split the dataset into training and testing sets
-X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.2, random_state=42)
+X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.1, random_state=1)
+categories = ['alt.atheism', 'comp.graphics', 'comp.os.ms-windows.misc','comp.sys.ibm.pc.hardware','comp.sys.mac.hardware', 'comp.windows.x','misc.forsale', 'rec.autos', 'rec.motorcycles','rec.sport.baseball', 'rec.sport.hockey', 'sci.crypt' ,'sci.electronics', 'sci.med', 'sci.space', 'soc.religion.christian', 'talk.politics.guns','talk.politics.mideast', 'talk.politics.misc','talk.religion.misc']
+# Training the data on these categories
+train = fetch_20newsgroups (subset='train', categories=categories)
+#MultinomialNaiveBayes functon
+class MultinomialNaiveBayes:
+    def __init__(self, alpha=0.01):
+        self.alpha = alpha
+        self.class_probs = None
+        self.feature_probs = None
+
+    def fit(self, X, y):
+        num_classes = len(np.unique(y))
+        num_features = X.shape[1]
+
+        # Calculate class probabilities
+        self.class_probs = np.zeros(num_classes)
+        for i in range(num_classes):
+            self.class_probs[i] = np.sum(y == i) / len(y)
+
+        # Calculate feature probabilities
+        self.feature_probs = np.zeros((num_classes, num_features))
+        for i in range(num_classes):
+            class_count = np.sum(y == i)
+            self.feature_probs[i, :] = (np.sum(X[y == i], axis=0) + self.alpha) / (class_count + self.alpha * num_features)
+
+    def predict(self, X):
+        num_samples = X.shape[0]
+        num_classes = len(self.class_probs)
+        predictions = np.zeros(num_samples, dtype=int)
 
+        for i in range(num_samples):
+            # Ensure X[i] is a 2D array with a single row
+            sample_probs = np.sum(np.log(self.feature_probs) * X[i, :].toarray(), axis=1) + np.log(self.class_probs)
+            predictions[i] = np.argmax(sample_probs)
+
+        return predictions
 # Define a list of classifiers to try
 classifiers = [
-    MultinomialNB(),
+    MultinomialNaiveBayes(alpha=.01),
     RandomForestClassifier(),
     SVC(),
     LogisticRegression()
 ]
-
+ma=0
+bar_values=[]
+bar_class=["MultinomialNB","RandomForestClassifier","SVC","LogisticRegression",]
+classifi=None
 for classifier in classifiers:
     # Create a pipeline with TF-IDF vectorizer and the current classifier
     model = make_pipeline(TfidfVectorizer(), classifier)
     
     # Train the model
-    model.fit(X_train, y_train)
+    model.fit(train.data, train.target)
 
     # Make predictions on the test set
     predictions = model.predict(X_test)
@@ -51,6 +91,8 @@ for classifier in classifiers:
     # Evaluate the performance of the model
     accuracy = accuracy_score(y_test, predictions)
     print(f"\nClassifier: {classifier.__class__.__name__}")
+    maxx=round(accuracy, 2)
+    bar_values.append(maxx)
     print(f"Accuracy: {accuracy:.2f}")
     
     # Display classification report
@@ -64,13 +106,38 @@ for classifier in classifiers:
     plt.ylabel('Actual')
     plt.title(f'Confusion Matrix - {classifier.__class__.__name__}')
     plt.show()
+    #getting best model train
+    if(maxx>ma):
+        ma=maxx
+        classifi=classifier
     print("\n\n\n")
-categories = ['alt.atheism', 'comp.graphics', 'comp.os.ms-windows.misc','comp.sys.ibm.pc.hardware','comp.sys.mac.hardware', 'comp.windows.x','misc.forsale', 'rec.autos', 'rec.motorcycles','rec.sport.baseball', 'rec.sport.hockey', 'sci.crypt' ,'sci.electronics', 'sci.med', 'sci.space', 'soc.religion.christian', 'talk.politics.guns','talk.politics.mideast', 'talk.politics.misc','talk.religion.misc']
-# Training the data on these categories
-train = fetch_20newsgroups (subset='train', categories=categories)
-def predict_category(Enter_artical, train=train, model=model):
-    print(Enter_artical)
-    pred=model.predict([Enter_artical])
+plt.xlabel('Model', fontweight ='bold', fontsize = 15) 
+plt.ylabel('Accuracy', fontweight ='bold', fontsize = 15)
+plt.bar(bar_class,bar_values, width = 0.4)
+# Annotating each bar with its value
+for i, value in enumerate(bar_values):
+    plt.text(i, value, f'{value:.2f}', ha='center', va='bottom', fontweight='bold')
+# best algo model is trained aagain 
+print(f"Best accuracy  model is {classifi}")
+model = make_pipeline(TfidfVectorizer(), classifi)
+    
+    # Train the model
+model.fit(train.data, train.target)
+
+    # Make predictions on the test set
+predictions = model.predict(X_test)
+    
+    # Evaluate the performance of the model
+accuracy = accuracy_score(y_test, predictions)
+print(f"\nClassifier: {classifi}")
+maxx=round(accuracy, 2)
+print(f"Accuracy: {accuracy:.2f}")
+    
+    # Display classification report
+print("Classification Report:\n", classification_report(y_test, predictions))
+conf_matrix = confusion_matrix(y_test, predictions)
+def predict_category(Enter_article, train=train, model=model):
+    pred=model.predict([Enter_article])
     return train.target_names[pred[0]]
 iface=gr.Interface(fn=predict_category,inputs=gr.Textbox(lines=10, placeholder="Enter text here"),outputs="text", title="Text Classification",description="getting... the categories of Artical/news")
 iface.launch(inline=False,share=True)