Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -3,15 +3,15 @@ import pandas as pd
|
|
| 3 |
import numpy as np
|
| 4 |
import matplotlib.pyplot as plt
|
| 5 |
import yfinance as yf
|
| 6 |
-
from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error
|
| 7 |
-
import math, warnings
|
| 8 |
import joblib
|
| 9 |
-
|
| 10 |
from tensorflow.keras.models import load_model
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
warnings.filterwarnings("ignore")
|
| 13 |
|
| 14 |
-
# Utility
|
| 15 |
def rmse(a, b):
|
| 16 |
return math.sqrt(mean_squared_error(a, b))
|
| 17 |
|
|
@@ -23,18 +23,18 @@ def download_data(ticker, start="2015-01-01", end=None):
|
|
| 23 |
df.rename(columns={'Close': 'close'}, inplace=True)
|
| 24 |
return df
|
| 25 |
|
| 26 |
-
# Forecast using
|
| 27 |
def forecast_models(ticker="AAPL", test_len=180):
|
| 28 |
df = download_data(ticker)
|
| 29 |
series = df['close']
|
| 30 |
train, test = series[:-test_len], series[-test_len:]
|
| 31 |
-
|
| 32 |
results = {}
|
| 33 |
|
| 34 |
-
# =====
|
| 35 |
try:
|
| 36 |
-
|
| 37 |
-
arima_forecast =
|
| 38 |
arima_forecast = pd.Series(arima_forecast, index=test.index)
|
| 39 |
results['ARIMA'] = {
|
| 40 |
"forecast": arima_forecast,
|
|
@@ -44,7 +44,7 @@ def forecast_models(ticker="AAPL", test_len=180):
|
|
| 44 |
except Exception as e:
|
| 45 |
results['ARIMA'] = {"error": str(e)}
|
| 46 |
|
| 47 |
-
# =====
|
| 48 |
try:
|
| 49 |
prophet_model = joblib.load("prophet_model.pkl")
|
| 50 |
future = prophet_model.make_future_dataframe(periods=len(test), freq='D')
|
|
@@ -58,28 +58,22 @@ def forecast_models(ticker="AAPL", test_len=180):
|
|
| 58 |
except Exception as e:
|
| 59 |
results['Prophet'] = {"error": str(e)}
|
| 60 |
|
| 61 |
-
# =====
|
| 62 |
try:
|
| 63 |
lstm_model = load_model("lstm_model.h5")
|
| 64 |
scaler = joblib.load("scaler.pkl")
|
| 65 |
scaled_series = scaler.transform(series.values.reshape(-1,1))
|
| 66 |
|
| 67 |
-
# Create sliding windows
|
| 68 |
window_size = 60
|
| 69 |
-
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
X = X.reshape((X.shape[0], X.shape[1],1))
|
| 76 |
-
return X, y
|
| 77 |
-
|
| 78 |
-
X_all, y_all = create_windows(scaled_series)
|
| 79 |
split_index = len(train) - window_size
|
| 80 |
-
X_test =
|
| 81 |
-
|
| 82 |
-
|
| 83 |
pred_scaled = lstm_model.predict(X_test, verbose=0)
|
| 84 |
pred = scaler.inverse_transform(pred_scaled)
|
| 85 |
lstm_forecast = pd.Series(pred.flatten(), index=test.index[:len(pred)])
|
|
@@ -107,7 +101,7 @@ def forecast_models(ticker="AAPL", test_len=180):
|
|
| 107 |
plt.savefig(plot_path)
|
| 108 |
plt.close()
|
| 109 |
|
| 110 |
-
# ===== Metrics
|
| 111 |
metrics = {}
|
| 112 |
for model_name, res in results.items():
|
| 113 |
if "RMSE" in res:
|
|
|
|
| 3 |
import numpy as np
|
| 4 |
import matplotlib.pyplot as plt
|
| 5 |
import yfinance as yf
|
|
|
|
|
|
|
| 6 |
import joblib
|
|
|
|
| 7 |
from tensorflow.keras.models import load_model
|
| 8 |
+
from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error
|
| 9 |
+
import math
|
| 10 |
+
import warnings
|
| 11 |
|
| 12 |
warnings.filterwarnings("ignore")
|
| 13 |
|
| 14 |
+
# Utility functions
|
| 15 |
def rmse(a, b):
|
| 16 |
return math.sqrt(mean_squared_error(a, b))
|
| 17 |
|
|
|
|
| 23 |
df.rename(columns={'Close': 'close'}, inplace=True)
|
| 24 |
return df
|
| 25 |
|
| 26 |
+
# Forecast using saved models
|
| 27 |
def forecast_models(ticker="AAPL", test_len=180):
|
| 28 |
df = download_data(ticker)
|
| 29 |
series = df['close']
|
| 30 |
train, test = series[:-test_len], series[-test_len:]
|
| 31 |
+
|
| 32 |
results = {}
|
| 33 |
|
| 34 |
+
# ====== ARIMA ======
|
| 35 |
try:
|
| 36 |
+
arima_model = joblib.load("arima_model.pkl")
|
| 37 |
+
arima_forecast = arima_model.forecast(steps=len(test))
|
| 38 |
arima_forecast = pd.Series(arima_forecast, index=test.index)
|
| 39 |
results['ARIMA'] = {
|
| 40 |
"forecast": arima_forecast,
|
|
|
|
| 44 |
except Exception as e:
|
| 45 |
results['ARIMA'] = {"error": str(e)}
|
| 46 |
|
| 47 |
+
# ====== Prophet ======
|
| 48 |
try:
|
| 49 |
prophet_model = joblib.load("prophet_model.pkl")
|
| 50 |
future = prophet_model.make_future_dataframe(periods=len(test), freq='D')
|
|
|
|
| 58 |
except Exception as e:
|
| 59 |
results['Prophet'] = {"error": str(e)}
|
| 60 |
|
| 61 |
+
# ====== LSTM ======
|
| 62 |
try:
|
| 63 |
lstm_model = load_model("lstm_model.h5")
|
| 64 |
scaler = joblib.load("scaler.pkl")
|
| 65 |
scaled_series = scaler.transform(series.values.reshape(-1,1))
|
| 66 |
|
|
|
|
| 67 |
window_size = 60
|
| 68 |
+
X, y = [], []
|
| 69 |
+
for i in range(window_size, len(scaled_series)):
|
| 70 |
+
X.append(scaled_series[i-window_size:i,0])
|
| 71 |
+
y.append(scaled_series[i,0])
|
| 72 |
+
X = np.array(X)
|
| 73 |
+
X = X.reshape((X.shape[0], X.shape[1], 1))
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
split_index = len(train) - window_size
|
| 75 |
+
X_test = X[split_index:]
|
| 76 |
+
|
|
|
|
| 77 |
pred_scaled = lstm_model.predict(X_test, verbose=0)
|
| 78 |
pred = scaler.inverse_transform(pred_scaled)
|
| 79 |
lstm_forecast = pd.Series(pred.flatten(), index=test.index[:len(pred)])
|
|
|
|
| 101 |
plt.savefig(plot_path)
|
| 102 |
plt.close()
|
| 103 |
|
| 104 |
+
# ===== Metrics table =====
|
| 105 |
metrics = {}
|
| 106 |
for model_name, res in results.items():
|
| 107 |
if "RMSE" in res:
|