Upload folder using huggingface_hub

.github/workflows/main.yml

@@ -28,7 +28,6 @@ jobs:
         run: |
           docker build -t ${{ secrets.DOCKER_USERNAME }}/dynamic-pricing:latest .
           docker push ${{ secrets.DOCKER_USERNAME }}/dynamic-pricing:latest
-
   deploy-to-huggingface:
     runs-on: ubuntu-latest
     needs: build-and-push

Dockerfile

@@ -17,4 +17,5 @@ COPY . .
 EXPOSE 8080 
 
 # Default command to run the application
-CMD ["uvicorn", "app:app"] 
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8080"]
+

app.py

@@ -15,6 +15,7 @@ import pandas as pd
 import sys
 from src.utils.main_utils.utils import load_object
 from src.utils.ml_utils.model.estimator import MLModel
+from src.pipeline.predict_pipeline import PredictPipeline
 from dotenv import load_dotenv
 import pymongo
 
@@ -51,24 +52,36 @@ async def train_route():
     except Exception as e:
         raise CustomException(e,sys)
     
+
 @app.post("/predict")
-async def predict_route(request: Request,file: UploadFile = File(...)):
+async def predict_route(request: Request, file: UploadFile = File(...)):
     try:
-        df=pd.read_csv(file.file)
-        preprocesor=load_object("final_model/preprocessor.pkl")
-        final_model=load_object("final_model/model.pkl")
-        network_model = MLModel(preprocessor=preprocesor,model=final_model)
-        print(df.iloc[0])
-        y_pred = network_model.predict(df)
-        print(y_pred)
-        df['predicted_column'] = y_pred
-        print(df['predicted_column'])
-        df.to_csv('prediction_output/output.csv')
-        table_html = df.to_html(classes='table table-striped')
+        df = pd.read_csv(file.file)
+
+        required_columns = [
+            "InvoiceNo", "StockCode", "Description", "Quantity", "InvoiceDate", "UnitPrice",
+            "CustomerID", "Country", "hour", "weekday", "week", "total_sales",
+            "peak_period_level", "overall_demand_level", "RecencySegment", "FrequencySegment",
+            "MonetarySegment", "country_purchasing_power", "sales_level_by_country",
+        ]
+
+        if not all(col in df.columns for col in required_columns):
+            return {"error": "Missing required input columns"}
+
+        predict_pipeline = PredictPipeline()
+        predictions = predict_pipeline.predict(df)
+
+        df["predicted_price"] = predictions 
+
+        df.to_csv("prediction_output/output.csv", index=False)
+
+        table_html = df.to_html(classes="table table-striped")
+
         return templates.TemplateResponse("table.html", {"request": request, "table": table_html})
-        
+
     except Exception as e:
-            raise CustomException(e,sys)
+        raise CustomException(e, sys)
+
     
 if __name__ == "__main__":
     app_run(host="localhost",port=8080,debug=True)

prediction_output/output.csv

@@ -1,6 +1,6 @@
-,InvoiceNo,StockCode,Description,Quantity,InvoiceDate,UnitPrice,CustomerID,Country,hour,weekday,week,total_sales,peak_period_level,overall_demand_level,RecencySegment,FrequencySegment,MonetarySegment,country_purchasing_power,sales_level_by_country,predicted_column
-0,536365,85123A,WHITE HANGING HEART T-LIGHT HOLDER,6,2010-12-01 08:26:00,2.55,17850.0,United Kingdom,8,2,48,15.3,Very Low,High,Very Low,Very Low,High,High,Very High,3.315773987352596
-1,536365,71053,WHITE METAL LANTERN,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,Medium,Very Low,Very Low,High,High,Very High,4.137054910286077
-2,536365,84406B,CREAM CUPID HEARTS COAT HANGER,8,2010-12-01 08:26:00,2.75,17850.0,United Kingdom,8,2,48,22.0,Very Low,High,Very Low,Very Low,High,High,Very High,3.5508847676251962
-3,536365,84029G,KNITTED UNION FLAG HOT WATER BOTTLE,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,High,Very Low,Very Low,High,High,Very High,4.438201940085351
-4,536365,84029E,RED WOOLLY HOTTIE WHITE HEART.,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,High,Very Low,Very Low,High,High,Very High,4.438201940085351
+InvoiceNo,StockCode,Description,Quantity,InvoiceDate,UnitPrice,CustomerID,Country,hour,weekday,week,total_sales,peak_period_level,overall_demand_level,RecencySegment,FrequencySegment,MonetarySegment,country_purchasing_power,sales_level_by_country,predicted_price
+536365,85123A,WHITE HANGING HEART T-LIGHT HOLDER,6,2010-12-01 08:26:00,2.55,17850.0,United Kingdom,8,2,48,15.3,Very Low,High,Very Low,Very Low,High,High,Very High,3.315773987352596
+536365,71053,WHITE METAL LANTERN,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,Medium,Very Low,Very Low,High,High,Very High,4.137054910286077
+536365,84406B,CREAM CUPID HEARTS COAT HANGER,8,2010-12-01 08:26:00,2.75,17850.0,United Kingdom,8,2,48,22.0,Very Low,High,Very Low,Very Low,High,High,Very High,3.5508847676251962
+536365,84029G,KNITTED UNION FLAG HOT WATER BOTTLE,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,High,Very Low,Very Low,High,High,Very High,4.438201940085351
+536365,84029E,RED WOOLLY HOTTIE WHITE HEART.,6,2010-12-01 08:26:00,3.39,17850.0,United Kingdom,8,2,48,20.34,Very Low,High,Very Low,Very Low,High,High,Very High,4.438201940085351

src/pipeline/predict_pipeline.py

@@ -1,56 +1,95 @@
-# import sys
-# import pandas as pd
-# from src.exception import CustomException
-# from utils import load_object
+import sys
+import pandas as pd
+from src.exception.exception import CustomException
+from src.utils.main_utils.utils import load_object
 
-# class PredictPipeline:
-#     def __init__(self):
-#         pass
+class PredictPipeline:
+    def __init__(self):
+        pass
 
-#     def predict(self,features):
-#         try:
-#             model_path = "artifacts\models.pkl"
-#             preprocessor_path = 'artifacts\preprocessor.pkl'
-#             model = load_object(file_path=model_path)
-#             preprocessor = load_object(file_path=preprocessor_path)
-#             data_scaled = preprocessor.transform(features)
-#             preds = model.predict(data_scaled)
-#             return preds
-#         except Exception as e:
-#             raise CustomException(e,sys)
+    def predict(self, features):
+        try:
+            model_path = "final_model/model.pkl"
+            preprocessor_path = "final_model/preprocessor.pkl"
+            
+            model = load_object(file_path=model_path)
+            preprocessor = load_object(file_path=preprocessor_path)
+            
+            data_scaled = preprocessor.transform(features)
+            preds = model.predict(data_scaled)
+            return preds
+        except Exception as e:
+            raise CustomException(e, sys)
 
-
-
-
-# class CustomData:
-#     def __init__(
-#             self ,
-#             gender:str,
-#             race_ethnicity:str,
-#             parental_level_of_education,
-#             lunch:str,
-#             test_preparation_course:str,
-#             reading_score:int,
-#             writing_score:int
-#     ):
-#         self.gender = gender
-#         self.race_ethnicity = race_ethnicity
-#         self.parental_level_of_education= parental_level_of_education
-#         self.lunch = lunch
-#         self.test_preparation_course = test_preparation_course
-#         self.reading_score = reading_score
-#         self.writing_score = writing_score
-
-#     def get_data_as_data_frame(self):
-#         try:
-#             custom_data_input_dict = {
-#                 "gender":[self.gender],
-#                 "race_ethnicity":[self.race_ethnicity],
-#                 "parental_level_of_education":[self.test_preparation_course],
-#                 "reading_score":[self.reading_score],
-#                 "writing_score":[self.writing_score]
-#             }
-#             return pd.DataFrame(custom_data_input_dict)
-#         except Exception as e:
-#             raise CustomException(e,sys)
-        
+class CustomData:
+    def __init__(
+        self,
+        InvoiceNo: int,
+        StockCode: str,
+        Description: str,
+        Quantity: int,
+        InvoiceDate: str,
+        UnitPrice: float,
+        CustomerID: float,
+        Country: str,
+        hour: int,
+        weekday: int,
+        week: int,
+        total_sales: float,
+        peak_period_level: str,
+        overall_demand_level: str,
+        RecencySegment: str,
+        FrequencySegment: str,
+        MonetarySegment: str,
+        country_purchasing_power: str,
+        sales_level_by_country: str,
+        adjusted_unit_price: float,
+    ):
+        self.InvoiceNo = InvoiceNo
+        self.StockCode = StockCode
+        self.Description = Description
+        self.Quantity = Quantity
+        self.InvoiceDate = InvoiceDate
+        self.UnitPrice = UnitPrice
+        self.CustomerID = CustomerID
+        self.Country = Country
+        self.hour = hour
+        self.weekday = weekday
+        self.week = week
+        self.total_sales = total_sales
+        self.peak_period_level = peak_period_level
+        self.overall_demand_level = overall_demand_level
+        self.RecencySegment = RecencySegment
+        self.FrequencySegment = FrequencySegment
+        self.MonetarySegment = MonetarySegment
+        self.country_purchasing_power = country_purchasing_power
+        self.sales_level_by_country = sales_level_by_country
+        self.adjusted_unit_price = adjusted_unit_price
+    
+    def get_data_as_data_frame(self):
+        try:
+            data_dict = {
+                "InvoiceNo": [self.InvoiceNo],
+                "StockCode": [self.StockCode],
+                "Description": [self.Description],
+                "Quantity": [self.Quantity],
+                "InvoiceDate": [self.InvoiceDate],
+                "UnitPrice": [self.UnitPrice],
+                "CustomerID": [self.CustomerID],
+                "Country": [self.Country],
+                "hour": [self.hour],
+                "weekday": [self.weekday],
+                "week": [self.week],
+                "total_sales": [self.total_sales],
+                "peak_period_level": [self.peak_period_level],
+                "overall_demand_level": [self.overall_demand_level],
+                "RecencySegment": [self.RecencySegment],
+                "FrequencySegment": [self.FrequencySegment],
+                "MonetarySegment": [self.MonetarySegment],
+                "country_purchasing_power": [self.country_purchasing_power],
+                "sales_level_by_country": [self.sales_level_by_country],
+                "adjusted_unit_price": [self.adjusted_unit_price],
+            }
+            return pd.DataFrame(data_dict)
+        except Exception as e:
+            raise CustomException(e, sys)