Modified Project

src/api/main.py

@@ -3,18 +3,23 @@ import os
 import sys
 src_directory = os.path.abspath(os.path.join(os.path.dirname(__file__), "../..", "src"))
 sys.path.append(src_directory)
-from modules import logistic_regression
+from modules import encoding_model
 
 app = FastAPI()
 
 @app.get("/")
 def home():
+    encoding_model.train_model()
     return {"message": "Welcome to Prediction Hub"}
 
 @app.get("/predict")
 def display_prediction(message : str = "Hello World"):
     try:
-        dimention  = logistic_regression.get_label(message)
+        dimention  = encoding_model.get_label(message)
         return dimention
     except Exception as e:
-        return f"Unable to fetch the data {e}"
+        return f"Unable to fetch the data {e}"
+    
+# @app.post("/predict")
+# def post_messsage(message, response_model ):
+#     logistic_regression.create_embending(message)

src/modules/encoding_model.py

@@ -0,0 +1,39 @@
+from sentence_transformers import SentenceTransformer
+model = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True)
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+import pandas as pd
+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
+
+encoding_model = model
+logreg_model = None
+X_train_embeddings = None
+
+file_path = r"src/data/sms_process_data_main.xlsx"
+df = sample_data.get_data_frame(file_path)
+
+def train_model():
+    logreg_model, X_train_embeddings
+
+    if logreg_model is None:
+        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.encode(X_train.tolist())
+        
+        logreg_model = LogisticRegression(max_iter=100)
+        logreg_model.fit(X_train_embeddings, y_train)
+
+def get_label(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)
+
+    no_of_dimensions = len(new_embeddings[0])
+    dimension_df = pd.DataFrame(new_embeddings[0], columns=["Dimension"])
+    return {"Prediction": prediction[0], "Prediction_Dimension": {no_of_dimensions: dimension_df}}

src/modules/logistic_regression.py

@@ -1,27 +1,33 @@
-from sentence_transformers import SentenceTransformer
-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
+# 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)
+# file_path = r"src/data/sms_process_data_main.xlsx"
+# df = sample_data.get_data_frame(file_path)
 
-def get_label(message):
-    X_train, X_test, y_train, y_test = train_test_split(df['MessageText'], df['label'], test_size=0.2, random_state=42)
-    model = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True)
-    X_train_embeddings = model.encode(X_train.tolist())
-    models = LogisticRegression(max_iter=100)
-    models.fit(X_train_embeddings, y_train)
-    new_embeddings = 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 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