138 lines
5.1 KiB
Python
Executable File
138 lines
5.1 KiB
Python
Executable File
import pandas as pd
|
|
import plotly.express as px
|
|
import plotly.graph_objects as go
|
|
import plotly.io as pio
|
|
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
|
|
import matplotlib
|
|
|
|
matplotlib.use('Agg')
|
|
import matplotlib.pyplot as plt
|
|
import io
|
|
import base64
|
|
from statsmodels.tsa.holtwinters import ExponentialSmoothing
|
|
import pmdarima as pm
|
|
from prophet import Prophet
|
|
|
|
|
|
def create_acf_pacf_plots(data):
|
|
# Create ACF and PACF plots using matplotlib
|
|
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(10, 8))
|
|
|
|
plot_acf(data, ax=ax1, lags=40)
|
|
ax1.set_title('Autocorrelation Function')
|
|
|
|
plot_pacf(data, ax=ax2, lags=40)
|
|
ax2.set_title('Partial Autocorrelation Function')
|
|
|
|
# Convert matplotlib plot to Plotly
|
|
buf = io.BytesIO()
|
|
plt.savefig(buf, format='png')
|
|
plt.close(fig)
|
|
buf.seek(0)
|
|
img_str = base64.b64encode(buf.getvalue()).decode('utf-8')
|
|
|
|
# Create Plotly figure with image
|
|
fig_plotly = go.Figure()
|
|
fig_plotly.add_layout_image(
|
|
dict(
|
|
source=f'data:image/png;base64,{img_str}',
|
|
x=0,
|
|
y=1,
|
|
xref="paper",
|
|
yref="paper",
|
|
sizex=1,
|
|
sizey=1,
|
|
sizing="stretch",
|
|
opacity=1,
|
|
layer="below"
|
|
)
|
|
)
|
|
fig_plotly.update_layout(
|
|
height=600,
|
|
showlegend=False,
|
|
xaxis=dict(visible=False),
|
|
yaxis=dict(visible=False)
|
|
)
|
|
return pio.to_html(fig_plotly, full_html=False)
|
|
|
|
|
|
def create_comparison_plot(filepath, forecast_history, selected_indices):
|
|
# Read data
|
|
if filepath.endswith('.csv'):
|
|
df = pd.read_csv(filepath)
|
|
else:
|
|
df = pd.read_excel(filepath)
|
|
|
|
date_col = df.columns[0]
|
|
value_col = df.columns[1]
|
|
df[date_col] = pd.to_datetime(df[date_col])
|
|
df.set_index(date_col, inplace=True)
|
|
|
|
# Create Plotly figure
|
|
fig = go.Figure()
|
|
fig.add_trace(go.Scatter(x=df.index, y=df[value_col], name='Historical', line=dict(color='black')))
|
|
|
|
# Use Plotly qualitative colors
|
|
colors = px.colors.qualitative.Plotly
|
|
|
|
# Generate forecasts for selected indices
|
|
for idx, run_idx in enumerate(selected_indices):
|
|
entry = forecast_history[run_idx]
|
|
train_percent = entry['train_percent'] / 100
|
|
forecast_periods = entry['forecast_periods']
|
|
model_type = entry['model_type']
|
|
|
|
# Split data
|
|
train_size = int(len(df) * train_percent)
|
|
test_size = len(df) - train_size
|
|
train_data = df[value_col].iloc[:train_size]
|
|
test_data = df[value_col].iloc[train_size:] if test_size > 0 else pd.Series()
|
|
forecast_dates = pd.date_range(start=df.index[-1], periods=forecast_periods + 1, freq=df.index.inferred_freq)[
|
|
1:]
|
|
|
|
# Run model based on model_type
|
|
forecast = None
|
|
if model_type == 'ARIMA':
|
|
model = pm.auto_arima(train_data,
|
|
seasonal=True,
|
|
m=12,
|
|
start_p=0, start_q=0,
|
|
max_p=3, max_q=3,
|
|
start_P=0, start_Q=0,
|
|
max_P=2, max_Q=2,
|
|
d=1, D=1,
|
|
trace=False,
|
|
error_action='ignore',
|
|
suppress_warnings=True,
|
|
stepwise=True)
|
|
model_fit = model.fit(train_data)
|
|
forecast = model_fit.predict(n_periods=forecast_periods)
|
|
|
|
elif model_type == 'Exponential Smoothing':
|
|
model = ExponentialSmoothing(train_data,
|
|
trend='add',
|
|
seasonal='add',
|
|
seasonal_periods=12)
|
|
model_fit = model.fit()
|
|
forecast = model_fit.forecast(forecast_periods)
|
|
|
|
elif model_type == 'Prophet':
|
|
prophet_df = train_data.reset_index().rename(columns={date_col: 'ds', value_col: 'y'})
|
|
model = Prophet(yearly_seasonality=True, weekly_seasonality=False, daily_seasonality=False)
|
|
model.add_seasonality(name='monthly', period=30.5, fourier_order=5)
|
|
model_fit = model.fit(prophet_df)
|
|
future = model.make_future_dataframe(periods=forecast_periods, freq=df.index.inferred_freq)
|
|
forecast_full = model_fit.predict(future)
|
|
forecast = forecast_full['yhat'].iloc[-forecast_periods:].values
|
|
|
|
# Add test data if available (only once to avoid clutter)
|
|
if test_size > 0 and idx == 0:
|
|
fig.add_trace(go.Scatter(x=df.index[train_size:], y=test_data, name='Test Data', line=dict(color='green')))
|
|
|
|
# Add forecast
|
|
label = f"Forecast Run {run_idx + 1}: {model_type}, {entry['train_percent']:.0f}/{entry['test_percent']:.0f}, {forecast_periods} periods"
|
|
fig.add_trace(go.Scatter(x=forecast_dates, y=forecast, name=label,
|
|
line=dict(dash='dash', color=colors[idx % len(colors)])))
|
|
|
|
fig.update_layout(title='Forecast Comparison', height=400, showlegend=True)
|
|
return pio.to_html(fig, full_html=False) |