Update app.py

app.py

@@ -1,48 +1,99 @@
-import gradio as gr
+import pandas as pd
+
+dataset = pd.read_csv('cancer.csv')
+
+x = dataset.drop(columns=["diagnosis(1=m, 0=b)"])
+
+y = dataset["diagnosis(1=m, 0=b)"]
+
+from sklearn.model_selection import train_test_split
+
+x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
+
 import tensorflow as tf
+
+model = tf.keras.models.Sequential()
+
+model.add(tf.keras.layers.Dense(256, input_shape=x_train.shape, activation='sigmoid'))
+model.add(tf.keras.layers.Dense(256, activation='sigmoid'))
+model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
+
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+
+model.fit(x_train, y_train, epochs=1000)
+
+model.evaluate(x_test, y_test)
+
+model.save("percyAI_model.h5")
+
+from google.colab import files
+files.download("percyAI_model.h5")
+
+from tensorflow.keras.models import load_model
+model = load_model("percyAI_model.h5")
+
 import numpy as np
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import layers
+
+x_values = np.random.randint(0, 100, (10000, 2))
+y_values = np.sum(x_values, axis=1)
+
+x_values = x_values / 100.0
+y_values = y_values / 200.0
+
+model = keras.Sequential([
+    layers.Dense(64, activation='relu', input_shape=(2,)),
+    layers.Dense(64, activation='relu'),
+    layers.Dense(1)
+])
+
+model.compile(optimizer='adam', loss='mse', metrics=['mae'])
+
+model.fit(x_values, y_values, epochs=30, batch_size=32, validation_split=0.2)
+
+test_input = np.array([[25, 30]]) / 100.0
+prediction = model.predict(test_input) * 200.0
+print("Predicted sum:", prediction[0][0])
+
+model.save("percyAI_model.h5")
+
+
+
+model.save("percyAI_model.h5")
+
+
+
+import gradio as gr
 import re
 
 BOT_NAME = "Phu Quy Ho"
 
-# Load your trained model (make sure percyAI_model.h5 is uploaded to your Space)
-model = tf.keras.models.load_model("percyAI_model.h5")
-
+# Basic math evaluator (with safety)
 def handle_math(user_input):
     user_input = user_input.lower().strip()
 
+    # Respond to greetings
     greetings = ["hi", "hello", "hey", "yo"]
     if any(greet in user_input for greet in greetings):
         return f"Hello! I am {BOT_NAME}. I can help you with math. Try something like: (3 + 5) * -2"
 
-    # Clean the input, only keep math symbols and digits
-    math_expression = re.sub(r"[^\d\.\+\-\*/\(\)\s]", "", user_input)
+    # Remove filler words like "what is"
+    math_expression = re.sub(r"[^\d\.\+\-\*/\(\)\s]", "", user_input)  # Strip out words, keep symbols
     math_expression = math_expression.replace("what is", "").strip()
 
     try:
-        # Try to evaluate simple math expressions
         result = eval(math_expression)
         return f"The answer is {result}"
     except:
-        # If that fails, optionally, try to use your ML model to predict sum (example)
-        try:
-            # Example: parse two numbers and predict their sum with ML model
-            numbers = [float(n) for n in re.findall(r"[-+]?\d*\.\d+|\d+", math_expression)]
-            if len(numbers) == 2:
-                x_input = np.array([numbers]) / 100.0  # normalize if model trained like that
-                pred = model.predict(x_input)
-                pred = pred[0][0] * 200.0  # scale back if needed
-                return f"My ML model predicts the sum is approximately: {pred:.2f}"
-        except:
-            pass
         return "Sorry, I couldn't understand that. Please enter a valid math expression like (2 + 3) * -1"
 
-demo = gr.Interface(
+# Gradio UI
+gr.Interface(
     fn=handle_math,
     inputs="text",
     outputs="text",
     title="Phu Quy Ho – Smart Math Solver",
     description="Say hello or ask me a math question! I support +, -, *, /, negative numbers, and parentheses."
-)
-
-demo.launch()
+).launch()