changes for uploading the model (#13)

- tech: model deploy (84b39ace0441cfe6fc3507689ef967c9bd88096b)

LSTM_model.py

@@ -20,7 +20,7 @@ def build_lstm_model(vocab_size, embedding_dim=64, max_len=10, lstm_units=128, d
 # Main function to execute the training process
 def main():
     # Path to your data file
-    data_path = r"E:\transactify\transactify\Dataset\transaction_data.csv"
+    data_path = r"E:\transactify\transactify\transactify\transactify\transactify\data_set\transaction_data.csv"
 
     # Preprocess the data
     sequences, labels, tokenizer, label_encoder = preprocess_data(data_path)

prediction.py → main.py

@@ -1,4 +1,4 @@
-# prediction.py
+# main.py
 import numpy as np
 import pandas as pd
 from tensorflow.keras.models import load_model

model.py

@@ -0,0 +1,25 @@
+from tensorflow.keras.models import load_model
+import joblib
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import numpy as np
+import re
+
+# Load the model, tokenizer, and label encoder
+model = load_model("transactify.h5")
+tokenizer = joblib.load("tokenizer.joblib")
+label_encoder = joblib.load("label_encoder.joblib")
+
+def clean_text(text):
+    text = text.lower()
+    text = re.sub(r"\d+", "", text)
+    text = re.sub(r"[^\w\s]", "", text)
+    return text.strip()
+
+def predict(text):
+    cleaned_text = clean_text(text)
+    sequence = tokenizer.texts_to_sequences([cleaned_text])
+    padded_sequence = pad_sequences(sequence, maxlen=100)
+    prediction = model.predict(padded_sequence)
+    predicted_label = np.argmax(prediction, axis=1)
+    category = label_encoder.inverse_transform(predicted_label)
+    return {"category": category[0]}

setup.md

@@ -47,7 +47,7 @@
 8. **Run the Prediction Code**:  
    To make predictions using the trained model, type:
    ```bash
-   python prediction.py
+   python main.py
    ```
 
 Following these steps will set up and run the Transactify model for predicting transaction categories based on descriptions.