Create app.py

app.py

@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+"""Text_Classification_Model_Deployment.ipynb
+Automatically generated by Colaboratory.
+Original file is located at
+    https://colab.research.google.com/drive/16FpeDQ0i5k_mttZZgxLDHVOMEd-6qGRU
+# **Text Classification Model Deployment using FastAPI and Gradio**
+"""
+
+"""- ### Importing Libraries"""
+
+# Basic imports for data manipulation and visualization
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+# scikit-learn imports for model loading and possibly preprocessing
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
+
+# Joblib or Pickle for loading your trained model
+import joblib
+import pickle
+
+import os
+print("Current Working Directory: ", os.getcwd())
+# List files in the current directory
+print("Files in Current Directory: ", os.listdir('.'))
+
+import nltk
+nltk.download('punkt')
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+nltk.download('stopwords')
+
+# Import the necessary libraries for preprocessing and deployment
+import re
+import joblib
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from fastapi import FastAPI
+
+# Define the custom function for text cleaning
+def clean_text(text):
+    # Remove HTML tags
+    text = re.sub(r'<.*?>', '', text)
+    # Remove non-alphabetic characters and lowercase the text
+    text = re.sub(r'[^a-zA-Z\s]', '', text, re.I|re.A).lower()
+    # Tokenization
+    tokens = text.split()
+    # Remove stopwords and lemmatize
+    lemmatizer = WordNetLemmatizer()
+    stop_words = set(stopwords.words('english'))
+    tokens = [lemmatizer.lemmatize(word) for word in tokens if word not in stop_words]
+    return ' '.join(tokens)
+
+# Load your trained model
+model = joblib.load('text_classification_LR_model (1).joblib')
+
+# Load the TF-IDF vectorizer
+tfidf_vectorizer = joblib.load('tfidf_vectorizer.joblib')
+
+# Preprocessing function for input text
+def preprocess(input_text):
+    # Apply text cleaning
+    input_text = clean_text(input_text)
+    input_text = [input_text]
+    # Transform input text using TF-IDF vectorizer
+    input_text = tfidf_vectorizer.transform(input_text)
+    return input_text
+
+# Predict the class for the input text
+def predict_class(input_text):
+    input_text = preprocess(input_text)
+    prediction = model.predict(input_text)
+    classes = ['World', 'Sports', 'Business', 'Sci/Tech']
+    predicted_class = classes[prediction[0]]
+    return predicted_class
+
+# FastAPI app
+app = FastAPI()
+
+@app.get('/')
+async def welcome():
+    return "Welcome to the Text Classification API"
+
+@app.post('/classify_text')
+async def classify_text(input_text: str):
+    prediction = predict_class(input_text)
+    return {"classification": prediction}
+
+import gradio as gr
+
+# Create Gradio interface
+iface = gr.Interface(fn=predict_class,
+                     inputs="text",
+                     outputs="text",
+                     title="Text Classification API",
+                     description="Enter text to classify it into categories: World, Sports, Business, Sci/Tech.")
+iface.launch()
+
+