Flask Deeployment Update

app.py

@@ -1,45 +1,44 @@
-from flask import Flask, render_template, request
-from PIL import Image
-import pickle
+from flask import Flask, request, render_template
+from src.Airbnb.pipelines.Prediction_Pipeline import CustomData, PredictPipeline
 
 app = Flask(__name__)
 
-# Load the model
-model = pickle.load(open("catboostalgo.pkl", "rb"))
-
 # Define the home route
 @app.route("/", methods=["GET", "POST"])
 def home():
     if request.method == "POST":
-        input_propertytype = int(request.form["propertytype"])
-        input_roomtype = int(request.form["roomtype"])
-        input_bedrooms = int(request.form["bedrooms"])
-        input_beds = int(request.form["beds"])
-        input_amenties = int(request.form["amenties"])
-        input_accommodates = int(request.form["accommodates"])
-        input_bathrooms = int(request.form["bathrooms"])
-        input_bedtype = int(request.form["bedtype"])
-        input_canceltype = int(request.form["canceltype"])
-        input_clean = int(request.form["clean"])
-        input_city = int(request.form["city"])
-        input_dp = int(request.form["dp"])
-        input_verify = int(request.form["verify"])
-        input_hostresponse = int(request.form["hostresponse"])
-        input_instbook = int(request.form["instbook"])
-        input_lat = float(request.form["lat"])
-        input_long = float(request.form["long"])
-        input_review = int(request.form["review"])
-        input_overallreview = int(request.form["overallreview"])
-
-        # Make a prediction
-        prediction = model.predict([[input_propertytype, input_roomtype, input_amenties, input_accommodates, input_bathrooms,
-                                      input_bedtype, input_canceltype, input_clean, input_city, input_dp, input_verify,
-                                      input_hostresponse, input_instbook, input_lat, input_long, input_review,
-                                      input_overallreview, input_bedrooms, input_beds]])
-
-        return str(prediction[0])
-
-    return render_template("index.html")
-
-if __name__ == "__main__":
-    app.run(debug=True,host="0.0.0.0",port=5000)
+        data = CustomData(
+            property_type=request.form.get("propertytype"),
+            room_type=request.form.get("roomtype"),
+            bedrooms=int(request.form.get("bedrooms")),
+            beds=int(request.form.get("beds")),
+            amenities=int(request.form.get("amenties")),
+            accommodates=int(request.form.get("accommodates")),
+            bathrooms=float(request.form.get("bathrooms")),
+            bed_type=request.form.get("bedtype"),
+            cancellation_policy=request.form.get("canceltype"),
+            cleaning_fee=float(request.form.get("clean")),
+            city=request.form.get("city"),
+            host_has_profile_pic=request.form.get("dp"),
+            host_identity_verified=request.form.get("verify"),
+            host_response_rate=request.form.get("hostresponse"),
+            instant_bookable=request.form.get("instbook"),
+            latitude=float(request.form.get("lat")),
+            longitude=float(request.form.get("long")),
+            number_of_reviews=int(request.form.get("review")),
+            review_scores_rating=float(request.form.get("overallreview"))
+        )
+
+        final_data = data.get_data_as_dataframe()
+
+        predict_pipeline = PredictPipeline()
+
+        pred = predict_pipeline.predict(final_data)
+
+        result = round(pred[0], 2)
+
+        return render_template("result.html", final_result=result)
+
+# Execution begins
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=8080, debug=True)

src/Airbnb/pipelines/Prediction_Pipeline.py

@@ -0,0 +1,97 @@
+import os
+import sys
+import pandas as pd
+from src.Airbnb.logger import logging
+from src.Airbnb.utils.utils import load_object
+from src.Airbnb.exception import customexception
+
+
+class PredictPipeline:
+    def __init__(self):
+        pass
+
+    def predict(self, features):
+        try:
+            preprocessor_path = os.path.join("Artifacts", "Preprocessor.pkl")
+            model_path = os.path.join("Artifacts", "Model.pkl")
+            preprocessor = load_object(preprocessor_path)
+            model = load_object(model_path)
+            logging.info('Preprocessor and Model Pickle files loaded')
+            scaled_data = preprocessor.transform(features)
+            logging.info('Data Scaled')
+            pred = model.predict(scaled_data)
+            return pred
+        except Exception as e:
+            raise customexception(e, sys)
+
+class CustomData:
+    def __init__(self,
+                 property_type: str,
+                 room_type: str,
+                 amenities: int,
+                 accommodates: int,
+                 bathrooms: float,
+                 bed_type: str,
+                 cancellation_policy: str,
+                 cleaning_fee: float,
+                 city: str,
+                 host_has_profile_pic: str,
+                 host_identity_verified: str,
+                 host_response_rate: str,
+                 instant_bookable: str,
+                 latitude: float,
+                 longitude: float,
+                 number_of_reviews: int,
+                 review_scores_rating: float,
+                 bedrooms: int,
+                 beds: int):
+
+        self.property_type = property_type
+        self.room_type = room_type
+        self.amenities = amenities
+        self.accommodates = accommodates
+        self.bathrooms = bathrooms
+        self.bed_type = bed_type
+        self.cancellation_policy = cancellation_policy
+        self.cleaning_fee = cleaning_fee
+        self.city = city
+        self.host_has_profile_pic = host_has_profile_pic
+        self.host_identity_verified = host_identity_verified
+        self.host_response_rate = host_response_rate
+        self.instant_bookable = instant_bookable
+        self.latitude = latitude
+        self.longitude = longitude
+        self.number_of_reviews = number_of_reviews
+        self.review_scores_rating = review_scores_rating
+        self.bedrooms = bedrooms
+        self.beds = beds
+
+    def get_data_as_dataframe(self):
+        try:
+            custom_data_input_dict = {
+                'property_type': [self.property_type],
+                'room_type': [self.room_type],
+                'amenities': [self.amenities],
+                'accommodates': [self.accommodates],
+                'bathrooms': [self.bathrooms],
+                'bed_type': [self.bed_type],
+                'cancellation_policy': [self.cancellation_policy],
+                'cleaning_fee': [self.cleaning_fee],
+                'city': [self.city],
+                'host_has_profile_pic': [self.host_has_profile_pic],
+                'host_identity_verified': [self.host_identity_verified],
+                'host_response_rate': [self.host_response_rate],
+                'instant_bookable': [self.instant_bookable],
+                'latitude': [self.latitude],
+                'longitude': [self.longitude],
+                'number_of_reviews': [self.number_of_reviews],
+                'review_scores_rating': [self.review_scores_rating],
+                'bedrooms': [self.bedrooms],
+                'beds': [self.beds]
+            }
+            df = pd.DataFrame(custom_data_input_dict)
+            logging.info('Dataframe Gathered')
+            return df
+        except Exception as e:
+            logging.info('Exception Occurred in prediction pipeline')
+            raise customexception(e, sys)