Upload 4 files

model2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678b4c76a08d15abce63e38b92c8152fbe8d0ba8130afa254b8a2cdd8be005f2
+size 165116144

model_ui.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import numpy as np
+import json
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import load_model
+
+import streamlit as st
+
+with open("./Model/tokenizer_cnnlstm.json", 'r') as tokenizer_file:
+    word_index = json.load(tokenizer_file)
+    tokenizer = Tokenizer(num_words=100000)
+    tokenizer.word_index = word_index
+
+model = load_model("./Model/model2.h5")
+
+classes = ['ADHD', 'OCD', 'Aspergers', 'Depression', 'PTSD']
+
+st.markdown("## Mental Health Prediction 😌 - **Beta**")
+
+st.divider()
+
+text = st.text_area("Enter transcript:", height=200) 
+
+if st.button("Predict"):
+    sequence = tokenizer.texts_to_sequences([text])
+    sequence = pad_sequences(sequence, maxlen=100)
+
+    prediction = model.predict(sequence)
+    predicted_class = classes[np.argmax(prediction)]
+    
+    st.write("**👉 I think you're talking about:**", predicted_class)
+
+    prediction_flat = prediction.flatten()
+
+    
+    data = pd.DataFrame({
+    'Category': classes,
+    'Values': prediction_flat})
+    
+    st.bar_chart(data.set_index('Category'))
+
+
+
+st.divider()
+
+st.markdown("### 🛑 Please give a context length of atleast 100 words for the best results")
+st.markdown("## Disclaimer:")
+st.markdown("""This model is not a substitute for professional medical advice. The predictions made by this model are based on a sample dataset and may not be accurate for all individuals. If you are concerned about your mental health, please 
+            consult witha qualified healthcare professional.""")

requirements.txt

@@ -0,0 +1,3 @@
+numpy==1.23.0
+tensorflow==2.12.0
+matplotlib