added prediction

src/api/main.py

@@ -12,14 +12,18 @@ def home():
     model = encoding_model.train_model()
     return {"message": "Welcome to Prediction Hub"}
 
-@app.get("/predict")
-def display_prediction(message : str = "Hello World"):
+@app.get("/dimention")
+def display_dimention(message : str = "Hello World"):
     try:
         dimention  = encoding_model.get_label(message)
         return dimention
     except Exception as e:
         return f"Unable to fetch the data {e}"
     
-# @app.post("/predict")
-# def post_messsage(message, response_model ):
-#     logistic_regression.create_embending(message)
+@app.get("/prediction")
+def display_prediction(message : str = "Give me a sms to predict"):
+    try:
+        prediction = encoding_model.get_prediction(message)
+        return prediction
+    except Exception as e:
+        return f"Unable to fetch the data {e}"

src/modules/encoding_model.py

@@ -35,8 +35,17 @@ def get_label(message):
     new_embeddings = encoding_model.encode([message])
     array = np.array(new_embeddings)[0].tolist()
 
-    prediction = logreg_model.predict(new_embeddings)
+    prediction = logreg_model.predict(new_embeddings).tolist()
 
     no_of_dimensions = len(new_embeddings[0])
     dimension_df = pd.DataFrame(array, columns=["Dimension"])
-    return {"Prediction_Dimension": {no_of_dimensions: dimension_df}}
+    
+    return {"Prediction_Dimension": {no_of_dimensions: dimension_df}}
+
+def get_prediction(message):
+    if logreg_model is None:
+        raise ValueError("Model has not been trained yet. Please call train_model first.")
+
+    new_embeddings = encoding_model.encode([message])
+    prediction = logreg_model.predict(new_embeddings).tolist()
+    return prediction

src/modules/logistic_regression.py

@@ -1,33 +0,0 @@
-# import pandas as pd
-# from sklearn.model_selection import train_test_split
-# from sklearn.linear_model import LogisticRegression
-# from sklearn.metrics import accuracy_score, classification_report
-# import numpy as np
-# import os
-# import sys
-# src_directory = os.path.abspath(os.path.join(os.path.dirname(__file__), "../..", "src"))
-# sys.path.append(src_directory)
-# from data import sample_data
-# from modules import encoding_model 
-
-# file_path = r"src/data/sms_process_data_main.xlsx"
-# df = sample_data.get_data_frame(file_path)
-
-# def get_label(message):
-#     from sentence_transformers import SentenceTransformer
-#     # model = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True)
-#     X_train, X_test, y_train, y_test = train_test_split(df['MessageText'], df['label'], test_size=0.2, random_state=42)
-#     X_train_embeddings = encoding_model.model.encode(X_train.tolist())
-#     models = LogisticRegression(max_iter=100)
-#     models.fit(X_train_embeddings, y_train)
-#     new_embeddings = encoding_model.model.encode(message)
-#     no_of_dimention = len(new_embeddings)
-#     array = np.array(new_embeddings).tolist()
-#     # new_predictions = models.predict(new_embeddings)
-#     dimention = pd.DataFrame(array,columns=["Dimention"])
-#     return {"Prediction_Dimention":{no_of_dimention: dimention}}
-
-# def create_embending(message:str):
-#     embending_message  = encoding_model.model.encode(message)
-#     result = np.array(embending_message).tolist()
-#     return result

src/schemas/schemas.py

@@ -0,0 +1,5 @@
+from pydantic import BaseModel
+
+class CosineSimilarity(BaseModel):
+    text_1 : str
+    text_1 : str