Update app.py

app.py

@@ -1,3 +1,5 @@
+#1. Importing Lib
+
 import numpy as np
 import pandas as pd
 from sklearn.model_selection import train_test_split
@@ -6,20 +8,23 @@ from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import accuracy_score
 import gradio as gr
 
-df=pd.read_csv("mail_data.csv")
+#2. Data Preprocessing
 
+df=pd.read_csv("mail_data.csv")
 
 df.loc[df["Category"]=="spam","Category",]=0
 df.loc[df["Category"]=="ham","Category",]=1
 
+# Spliting Data into xand y
+
 x=df["Message"]
 y=df["Category"]
 
-
-
+#3. Modeling Part
 
 x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
 
+# Features extractions using TfidfVectorizer
 feature_extraction=TfidfVectorizer(min_df=1,stop_words="english",lowercase=True)
 
 x_train_features = feature_extraction.fit_transform(x_train)
@@ -31,24 +36,16 @@ y_test = y_test.astype("int")
 
 
 model=LogisticRegression()
-
+# Trains the model only at Train data features
 model.fit(x_train_features,y_train)
 
-
-
 x_predict=model.predict(x_train_features)
 x_accuracy=accuracy_score(x_predict,y_train)
 
-
 y_predict=model.predict(x_test_features)
 y_accuracy=accuracy_score(y_predict,y_test)
 
-
-
-
-
-
-
+#4. UI For Model
 
 # Function to predict whether the email is spam or ham
 def classify_email(email_text):