Add models and update application file

app.py

@@ -1,7 +1,87 @@
 import gradio as gr
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+import pickle
+import spacy
+from tqdm import tqdm
+import gc
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load models
+model_1 = tf.keras.models.load_model("model_1.h5")
+model_2 = tf.keras.models.load_model("model_2.h5")
+model_3 = tf.keras.models.load_model("model_3.h5")
+model_4 = tf.keras.models.load_model("model_4.h5")
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Load dictionaries
+with open('word_dict.pkl', 'rb') as f:
+    word_dict = pickle.load(f)
+
+with open('lemma_dict.pkl', 'rb') as f:
+    lemma_dict = pickle.load(f)
+
+# Load SpaCy NLP model
+nlp = spacy.load('en_core_web_lg', disable=['parser', 'ner', 'tagger'])
+nlp.vocab.add_flag(lambda s: s.lower() in spacy.lang.en.stop_words.STOP_WORDS, spacy.attrs.IS_STOP)
+
+def preprocess_text(text):
+    """Preprocess the input text using SpaCy and return word indices."""
+    doc = nlp(text)
+    word_seq = []
+    for token in doc:
+        if token.pos_ != "PUNCT":
+            if token.text not in word_dict:
+                word_dict[token.text] = len(word_dict) + 1  # Increment index
+            word_seq.append(word_dict[token.text])
+    return word_seq
+
+def classify_question(text):
+    # Preprocess the text
+    seq = preprocess_text(text)
+    padded_seq = tf.keras.preprocessing.sequence.pad_sequences([seq], maxlen=50)  # Adjust maxlen if needed
+
+    # Get predictions from each model
+    pred1 = 0.15 * np.squeeze(model_1.predict(padded_seq, batch_size=1, verbose=0))
+    pred2 = 0.35 * np.squeeze(model_2.predict(padded_seq, batch_size=1, verbose=0))
+    pred3 = 0.15 * np.squeeze(model_3.predict(padded_seq, batch_size=1, verbose=0))
+    pred4 = 0.35 * np.squeeze(model_4.predict(padded_seq, batch_size=1, verbose=0))
+
+    # Combine predictions
+    avg_pred = pred1 + pred2 + pred3 + pred4
+    label = "Insincere" if avg_pred > 0.5 else "Sincere"
+
+    # Create a list of probabilities for each model
+    probs = {
+        "Model 1 Probability": float(pred1),
+        "Model 2 Probability": float(pred2),
+        "Model 3 Probability": float(pred3),
+        "Model 4 Probability": float(pred4),
+        "Average Probability": float(avg_pred)
+    }
+
+    return label, probs
+
+# Example questions
+example_questions = [
+    "Is this the best place to get information?",
+    "I need help with my homework.",
+    "Why do people ask such stupid questions?",
+    "Can you tell me the answer to life?"
+]
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=classify_question,
+    inputs=[
+        gr.inputs.Textbox(lines=2, placeholder="Enter your question here..."),
+        gr.inputs.Dropdown(example_questions, label="Select an example question:")
+    ],
+    outputs=[
+        "text",  # Output for label
+        "json"   # Output for probabilities
+    ],
+    title="Quora Insincere Questions Classifier",
+    description="Enter your question to classify it as sincere or insincere. Select an example question from the dropdown."
+)
+
+interface.launch()

lemma_dict.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2574d160d8550bf671f6588a1d32e28fab2f0610b526f4f09106e0ae99e9849c
+size 6362111

model_1.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36dfda896de06192843447fdf71b4bc5a72f46a4fc788dfb080a767af6b974c
+size 749650112

model_2.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d0c6ce351d7ba21b6ae5392768abf2ca44bfe22261d5d0a54109dedb6ed6c3
+size 749650112

model_3.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a96ee5741ecf16149d3ca66e82634a5c46b42e42d939321bd1468f856c00d90
+size 749650016

model_4.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b579d0565f632ae2a1fb53e02e0d0f452d85db7a7238bcff445644cde92b9c4
+size 749650016

word_dict.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abb8d9104762746b16fa989592b247332fb563b1c8be89edc2829c4d2aec513
+size 4555634