Create app.py

app.py

@@ -0,0 +1,92 @@
+import streamlit as st
+import re
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.model_selection import train_test_split
+
+# Load your symptom-disease data
+data = pd.read_csv("Symptom2Disease.csv")
+
+# Initialize the TF-IDF vectorizer
+tfidf_vectorizer = TfidfVectorizer()
+
+# Apply TF-IDF vectorization to the preprocessed text data
+X = tfidf_vectorizer.fit_transform(data['text'])
+
+# Split the dataset into a training set and a testing set
+X_train, X_test, y_train, y_test = train_test_split(X, data['label'], test_size=0.2, random_state=42)
+
+# Initialize the Multinomial Naive Bayes model
+model = MultinomialNB()
+
+# Train the model on the training data
+model.fit(X_train, y_train)
+
+# Set Streamlit app title with emojis
+st.title("Health Symptom-to-Disease Predictor 🏥👨‍⚕️")
+
+# Define a sidebar
+st.sidebar.title("Tool Definition")
+st.sidebar.markdown("__Tool Definition__")
+st.sidebar.markdown("This tool helps you identify possible diseases based on the symptoms you provide.")
+st.sidebar.markdown("This is my project for the KaggleX program.")
+st.sidebar.markdown("Please note that this tool is for informational purposes only. Always consult a healthcare professional for accurate medical advice.")
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Function to preprocess user input
+def preprocess_input(user_input):
+    user_input = user_input.lower()  # Convert to lowercase
+    user_input = re.sub(r"[^a-zA-Z\s]", "", user_input)  # Remove special characters and numbers
+    user_input = " ".join(user_input.split())  # Remove extra spaces
+    return user_input
+
+# Function to predict diseases based on user input
+def predict_diseases(user_clean_text):
+    user_input_vector = tfidf_vectorizer.transform([user_cleaned_text])  # Vectorize the cleaned user input
+    predictions = model.predict(user_input_vector)  # Make predictions using the trained model
+    return predictions
+
+# Add user input section
+user_input = st.text_area("Enter your symptoms (how you feel):", key="user_input")
+
+# Add button to predict disease
+if st.button("Predict Disease"):
+    # Display loading message
+    with st.spinner("Diagnosing patient..."):
+        # Check if user input is not empty
+        if user_input:
+            cleaned_input = preprocess_input(user_input)
+            predicted_diseases = predict_diseases(cleaned_input)
+
+            # Display predicted diseases
+            st.session_state.messages.append({"role": "user", "content": user_input})
+            st.session_state.messages.append({"role": "assistant", "content": f"Based on your symptoms, you might have {', '.join(predicted_diseases)}."})
+
+            st.write("Based on your symptoms, you might have:")
+            for disease in predicted_diseases:
+                st.write(f"- {disease}")
+        else:
+            st.warning("Please enter your symptoms before predicting.")
+
+# Display a warning message
+st.warning("Please note that this tool is for informational purposes only. Always consult a healthcare professional for accurate medical advice.")
+
+# Create FAQs section
+show_faqs = st.checkbox("Show FAQs")
+if show_faqs:
+    st.markdown("## Frequently Asked Questions")
+    st.markdown("**Q: How does this tool work?**")
+    st.markdown("A: The tool uses a machine learning model to analyze the symptoms you enter and predicts possible diseases based on a pre-trained dataset.")
+
+    st.markdown("**Q: Is this a substitute for a doctor's advice?**")
+    st.markdown("A: No, this tool is for informational purposes only. It's essential to consult a healthcare professional for accurate medical advice.")
+
+    st.markdown("**Q: Can I trust the predictions?**")
+    st.markdown("A: While the tool provides predictions, it's not a guarantee of accuracy. It's always best to consult a healthcare expert for a reliable diagnosis.")
+
+# Add attribution
+st.markdown("Created with ❤️ by Joas")