Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from gradio_app_builder import app
|
2 |
+
import yfinance as yf
|
3 |
+
from sklearn.linear_model import LinearRegression
|
4 |
+
import json
|
5 |
+
|
6 |
+
@app.route("/")
|
7 |
+
def train_predict_wrapper(ticker, start_date, end_date, prediction_days):
|
8 |
+
"""
|
9 |
+
Downloads stock data, trains a linear regression model, and predicts future prices.
|
10 |
+
|
11 |
+
Args:
|
12 |
+
ticker: The ticker symbol of the stock.
|
13 |
+
start_date: The start date for the data (YYYY-MM-DD format).
|
14 |
+
end_date: The end date for the data (YYYY-MM-DD format).
|
15 |
+
prediction_days: The number of days to predict.
|
16 |
+
|
17 |
+
Returns:
|
18 |
+
A list of predicted closing prices for the next `prediction_days`.
|
19 |
+
"""
|
20 |
+
# Download stock data
|
21 |
+
data = yf.download(ticker, start=start_date, end=end_date)
|
22 |
+
# Extract closing price and set as index
|
23 |
+
data = data["Close"].to_frame().set_index(data.index.values)
|
24 |
+
|
25 |
+
# Train linear regression model
|
26 |
+
X = data.index.values[:-prediction_days].reshape(-1, 1)
|
27 |
+
y = data.values[:-prediction_days]
|
28 |
+
model = LinearRegression()
|
29 |
+
model.fit(X, y)
|
30 |
+
|
31 |
+
# Predict future prices
|
32 |
+
future_dates = data.index.values[-prediction_days:]
|
33 |
+
X_future = future_dates.reshape(-1, 1)
|
34 |
+
predicted_prices = model.predict(X_future).tolist()
|
35 |
+
|
36 |
+
# Return predicted prices as JSON
|
37 |
+
return json.dumps(predicted_prices)
|
38 |
+
|
39 |
+
# Launch the Gradio application
|
40 |
+
app.launch()
|