Spaces:
Sleeping
Sleeping
Delete app .py
Browse files
app .py
DELETED
@@ -1,77 +0,0 @@
|
|
1 |
-
# -*- coding: utf-8 -*-
|
2 |
-
"""app.ipynb
|
3 |
-
|
4 |
-
Automatically generated by Colab.
|
5 |
-
|
6 |
-
Original file is located at
|
7 |
-
https://colab.research.google.com/drive/1vvN4x-mEuGtdgL2zlzu2ci6sercypfCa
|
8 |
-
"""
|
9 |
-
|
10 |
-
import numpy as np
|
11 |
-
import pandas as pd
|
12 |
-
import gradio as gr
|
13 |
-
from keras.models import Sequential
|
14 |
-
from keras.layers import SimpleRNN, Dense
|
15 |
-
from sklearn.preprocessing import MinMaxScaler
|
16 |
-
|
17 |
-
# Generate dummy stock price data
|
18 |
-
def generate_dummy_data():
|
19 |
-
np.random.seed(0)
|
20 |
-
time_steps = 100
|
21 |
-
x = np.linspace(0, 20, time_steps)
|
22 |
-
prices = 50 + np.sin(x) * 10 + np.random.normal(0, 1, time_steps)
|
23 |
-
return prices
|
24 |
-
|
25 |
-
# Preprocess data
|
26 |
-
def prepare_data(data, window_size):
|
27 |
-
X, y = [], []
|
28 |
-
for i in range(len(data) - window_size):
|
29 |
-
X.append(data[i:i + window_size])
|
30 |
-
y.append(data[i + window_size])
|
31 |
-
return np.array(X), np.array(y)
|
32 |
-
|
33 |
-
# Create and train RNN model
|
34 |
-
def train_model():
|
35 |
-
raw_prices = generate_dummy_data().reshape(-1, 1)
|
36 |
-
scaler = MinMaxScaler()
|
37 |
-
scaled_prices = scaler.fit_transform(raw_prices)
|
38 |
-
|
39 |
-
window_size = 5
|
40 |
-
X, y = prepare_data(scaled_prices, window_size)
|
41 |
-
X = X.reshape((X.shape[0], X.shape[1], 1))
|
42 |
-
|
43 |
-
model = Sequential([
|
44 |
-
SimpleRNN(50, activation='relu', input_shape=(window_size, 1)),
|
45 |
-
Dense(1)
|
46 |
-
])
|
47 |
-
|
48 |
-
model.compile(optimizer='adam', loss='mse')
|
49 |
-
model.fit(X, y, epochs=30, verbose=0)
|
50 |
-
|
51 |
-
return model, scaler, window_size
|
52 |
-
|
53 |
-
model, scaler, window_size = train_model()
|
54 |
-
|
55 |
-
# Prediction function for Gradio
|
56 |
-
def predict_next_prices(inputs):
|
57 |
-
inputs = [float(i) for i in inputs.split(',')]
|
58 |
-
if len(inputs) != window_size:
|
59 |
-
return f"Please enter {window_size} comma-separated values."
|
60 |
-
|
61 |
-
input_array = np.array(inputs).reshape(-1, 1)
|
62 |
-
scaled_input = scaler.transform(input_array).reshape((1, window_size, 1))
|
63 |
-
scaled_prediction = model.predict(scaled_input)[0][0]
|
64 |
-
predicted_price = scaler.inverse_transform([[scaled_prediction]])[0][0]
|
65 |
-
return f"Predicted Next Price: ₹{predicted_price:.2f}"
|
66 |
-
|
67 |
-
# Gradio Interface
|
68 |
-
demo = gr.Interface(
|
69 |
-
fn=predict_next_prices,
|
70 |
-
inputs=gr.Textbox(label=f"Enter last {window_size} stock prices (comma-separated)"),
|
71 |
-
outputs="text",
|
72 |
-
title="RNN Stock Price Predictor (Dummy Data)",
|
73 |
-
description="Enter previous prices to predict the next value."
|
74 |
-
)
|
75 |
-
|
76 |
-
if __name__ == "__main__":
|
77 |
-
demo.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|