made changes to model

app.py

@@ -1,4 +1,6 @@
 import nltk
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
 from fastapi import FastAPI
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel
@@ -8,9 +10,19 @@ import joblib
 nltk.download('wordnet', quiet=True)
 nltk.download('stopwords', quiet=True)
 
+# Initialize lemmatizer
+lemmatizer = WordNetLemmatizer()
+
 # Load the trained model
 model = joblib.load('disaster_classification_model.joblib')
 
+def improved_preprocess(text):
+    text = text.lower()
+    text = ''.join([char for char in text if char not in string.punctuation])
+    words = text.split()
+    words = [lemmatizer.lemmatize(word) for word in words if word not in stopwords.words('english')]
+    return ' '.join(words)
+
 app = FastAPI()
 
 class TextRequest(BaseModel):
@@ -18,11 +30,11 @@ class TextRequest(BaseModel):
 
 @app.post("/predict")
 async def predict(request: TextRequest):
-    text = request.text
-    # The preprocessing is now handled by the loaded pipeline
-    prediction = model.predict([text])[0]
-    result = "disaster" if prediction == 1 else "not"
-    return JSONResponse(content={"output": result})
+     text = request.text
+     new_text_processed = [improved_preprocess(text)]
+     prediction = model.predict(new_text_processed)
+     result = "disaster" if prediction == 1 else "not"
+     return JSONResponse(content={"output": result})
 
 @app.get("/")
 async def root():

testmodel.py

@@ -0,0 +1,14 @@
+import joblib
+
+# Load the trained model
+model = joblib.load('disaster_classification_model.joblib')
+
+# Sample text to test
+text = "This is a test message to check the model."
+
+# Make prediction
+prediction = model.predict([text])[0]
+
+# Print result
+result = "disaster" if prediction == 1 else "not"
+print(f"Prediction: {result}")