Update app.py

app.py

@@ -1,33 +1,40 @@
-#1. Importing Lib
+# importing lib
+
+import gradio as gr
 import numpy as np
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score
-import gradio as gr
 
-#2. Data Preprocessing
-df=pd.read_csv("mail_data (1).csv")
+#Data Preprocessing
+
+df=pd.read_csv("mail_data.csv")
 
-df.loc[df["Category"]=="spam","Category",]=0
-df.loc[df["Category"]=="ham","Category",]=1
+df.loc[df["Category"]=="spam","Category"]=0
+df.loc[df["Category"]=="ham","Category"]=1
 
-# split data into dependent and independednt
 x=df["Message"]
 y=df["Category"]
 
-#3. Modeling Part
+
+
+
+# Modeling part
+
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
 
-# Vectorization process for message content
+# Features extraction using TfidfVectorizer
+
 feature_extraction=TfidfVectorizer(min_df=1,stop_words="english",lowercase=True)
 
-x_train_features = feature_extraction.fit_transform(x_train)
-x_test_features  =  feature_extraction.transform(x_test)
+x_train_features=feature_extraction.fit_transform(x_train)
+x_test_features=feature_extraction.transform(x_test)
+
 
-y_train = y_train.astype("int")
-y_test = y_test.astype("int")
+y_train=y_train.astype('int')
+y_test=y_test.astype('int')
 
 
 
@@ -35,7 +42,6 @@ model=LogisticRegression()
 model.fit(x_train_features,y_train)
 
 
-
 x_predict=model.predict(x_train_features)
 x_accuracy=accuracy_score(x_predict,y_train)
 
@@ -43,23 +49,24 @@ y_predict=model.predict(x_test_features)
 y_accuracy=accuracy_score(y_predict,y_test)
 
 
-#4. Gradio Part 
+
+# UI for the Model
 
 # Function to predict whether the email is spam or ham
 def classify_email(email_text):
     # Transform the input email text using the same vectorizer used during training
     input_data_features = feature_extraction.transform([email_text])
-
+    
     # Predict using the trained model
     prediction = model.predict(input_data_features)
-
+    
     # Return the result based on the prediction
     if prediction[0] == 0:
         return "Your email is Spam"
     else:
         return "Your email is Ham"
 
-# Create a Gradio interface for user input
+# Create the Gradio interface
 interface = gr.Interface(
     fn=classify_email,  # Function to be called when user interacts
     inputs=gr.Textbox(label="Enter your email text here", placeholder="Type your email...", lines=5),
@@ -69,4 +76,4 @@ interface = gr.Interface(
 
 # Launch the interface
 interface.launch()
-
+