Initial commit

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import pandas as pd
+from prophet import Prophet
+import plotly.graph_objs as go
+import re
+
+# Dictionary to map Russian month names to month numbers
+russian_months = {
+    "январь": "01",
+    "февраль": "02",
+    "март": "03",
+    "апрель": "04",
+    "май": "05",
+    "июнь": "06",
+    "июль": "07",
+    "август": "08",
+    "сентябрь": "09",
+    "октябрь": "10",
+    "ноябрь": "11",
+    "декабрь": "12"
+}
+
+def read_and_process_file(file):
+    # Read the first three lines as a single text string
+    with open(file.name, 'r') as f:
+        first_three_lines = ''.join([next(f) for _ in range(3)])
+    
+    # Check for "Неделя" or "Week" (case-insensitive)
+    if not any(word in first_three_lines.lower() for word in ["неделя", "week"]):
+        period_type = "Month"
+    else:
+        period_type = "Week"
+
+    # Read the file again to process it
+    with open(file.name, 'r') as f:
+        lines = f.readlines()
+    
+    # Check if the second line is empty
+    if lines[1].strip() == '':
+        source = 'Google'
+        data = pd.read_csv(file.name, skiprows=2)
+        # Replace any occurrences of "<1" with 0
+    else:
+        source = 'Yandex'
+        data = pd.read_csv(file.name, sep=';', skiprows=0, usecols=[0, 2])
+        if period_type == "Month":
+            # Replace Russian months with yyyy-MM format
+            data.iloc[:, 0] = data.iloc[:, 0].apply(lambda x: re.sub(r'(\w+)\s(\d{4})', lambda m: f'{m.group(2)}-{russian_months[m.group(1).lower()]}', x) + '-01')
+        if period_type == "Week":
+            data.iloc[:, 0] = pd.to_datetime(data.iloc[:, 0], format="%d.%m.%Y")
+        # Replace any occurrences of "<1" with 0
+    data.iloc[:, 1] = data.iloc[:, 1].str.replace('<1', '0').str.replace(' ', '').str.replace(',', '.').astype(float)
+    
+    # Process the date column and set it as the index
+    period_col = data.columns[0]
+    data[period_col] = pd.to_datetime(data[period_col])
+    data.set_index(period_col, inplace=True)
+    
+    return data, period_type, period_col
+
+def forecast_time_series(file):
+    data, period_type, period_col = read_and_process_file(file)
+
+    if period_type == "Month":
+        year = 12
+        n_periods = 24
+        freq = "MS"
+    else:
+        year = 52
+        n_periods = year * 2  # Number of periods to forecast
+        freq = "W"
+
+    # Prepare data for Prophet
+    df = data.reset_index().rename(columns={period_col: 'ds', data.columns[0]: 'y'})
+
+    # Fit the Prophet model
+    model = Prophet()
+    model.fit(df)
+
+    # Create future dataframe
+    future = model.make_future_dataframe(periods=n_periods, freq=freq)
+    
+    # Forecasting
+    forecast = model.predict(future)
+    
+    # Calculate the YoY change
+    sum_last_year_original = df['y'].iloc[-year:].sum()
+    sum_first_year_forecast = forecast['yhat'].iloc[-n_periods:-n_periods + year].sum()
+    yoy_change = (sum_first_year_forecast - sum_last_year_original) / sum_last_year_original
+
+    # Create an interactive plot with Plotly
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=data.index, y=data.iloc[:, 0], mode='lines', name='Observed'))
+    fig.add_trace(go.Scatter(x=forecast['ds'], y=forecast['yhat'], mode='lines', name='Forecast', line=dict(color='red')))
+    fig.add_trace(go.Scatter(
+        x=forecast['ds'],
+        y=forecast['yhat_lower'],
+        fill=None,
+        mode='lines',
+        line=dict(color='pink'),
+        # showlegend=False,
+        name='Lower CI'
+    ))
+    fig.add_trace(go.Scatter(
+        x=forecast['ds'],
+        y=forecast['yhat_upper'],
+        fill='tonexty',
+        mode='lines',
+        line=dict(color='pink'),
+        name='Upper CI'
+    ))
+    fig.update_layout(
+        title='Observed Time Series and Forecast with Confidence Intervals',
+        xaxis_title='Date',
+        yaxis_title='Values',
+        legend=dict(
+            orientation='h',
+            yanchor='bottom',
+            y=1.02,
+            xanchor='right',
+            x=1
+        ),
+        hovermode='x unified'
+    )
+    
+    # Combine original data and forecast data into one DataFrame for export
+    combined_df = pd.concat([data, forecast.set_index('ds')[['yhat', 'yhat_lower', 'yhat_upper']]], axis=1)
+    combined_file = 'combined_data.csv'
+    combined_df.to_csv(combined_file)
+
+    # Return plot, YoY change, and file path for export
+    return fig, f'Year-over-Year Change in Sum of Values: {yoy_change:.2%}', combined_file
+
+# Create Gradio interface using Blocks
+with gr.Blocks(theme=gr.themes.Monochrome()) as interface:
+    gr.Markdown("# Time Series Forecasting")
+    gr.Markdown("Upload a CSV file with a time series to forecast the next 2 years and see the YoY % change. Download the combined original and forecast data.")
+    
+    with gr.Row():
+        file_input = gr.File(label="Upload Time Series CSV")
+    
+    with gr.Row():
+        plot_output = gr.Plot(label="Time Series + Forecast Chart")
+    
+    with gr.Row():
+        yoy_output = gr.Text(label="YoY % Change")
+    
+    with gr.Row():
+        csv_output = gr.File(label="Download Combined Data CSV")
+    
+    file_input.change(forecast_time_series, inputs=file_input, outputs=[plot_output, yoy_output, csv_output])
+
+# Launch the interface
+interface.launch(debug=True)

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+pandas
+plotly
+prophet