Update app.py
Browse files
app.py
CHANGED
@@ -1,93 +1,12 @@
|
|
1 |
-
import streamlit as st
|
2 |
import pandas as pd
|
3 |
-
|
4 |
-
import numpy as np
|
5 |
-
from itertools import product
|
6 |
-
from io import BytesIO
|
7 |
-
|
8 |
-
# Function to run the Exponential Smoothing Model
|
9 |
-
def run_exp_smoothing(city_data, trend, damped_trend, seasonal, seasonal_period):
|
10 |
-
try:
|
11 |
-
model = ExponentialSmoothing(city_data, trend=trend, damped_trend=damped_trend, seasonal=seasonal, seasonal_periods=seasonal_period)
|
12 |
-
model_fit = model.fit(optimized=True)
|
13 |
-
return model_fit.forecast(steps=6), model_fit.aic
|
14 |
-
except Exception as e:
|
15 |
-
return None, None
|
16 |
-
|
17 |
-
def create_data():
|
18 |
-
data = pd.read_csv('accident_count.csv', parse_dates=True, index_col=0)
|
19 |
-
data.index = pd.to_datetime(data.index, format='%Y%m')
|
20 |
-
data = data.groupby('City').resample('M').sum().reset_index()
|
21 |
-
#data = data[data['City'] == 'ARAR']
|
22 |
-
data.index = data['Accident Month Bracket']
|
23 |
-
data = data.drop(['Accident Month Bracket'],axis=1)
|
24 |
-
data.index = data.index.strftime('%Y-%m')
|
25 |
-
return data
|
26 |
-
|
27 |
-
# Function to convert DataFrame to Excel
|
28 |
-
def to_excel(df):
|
29 |
-
output = BytesIO()
|
30 |
-
writer = pd.ExcelWriter(output, engine='xlsxwriter')
|
31 |
-
df.to_excel(writer, sheet_name='Sheet1')
|
32 |
-
writer.save()
|
33 |
-
processed_data = output.getvalue()
|
34 |
-
return processed_data
|
35 |
-
|
36 |
-
|
37 |
-
st.title("Exponential Smoothing Forecasting")
|
38 |
-
# Upload Data Section
|
39 |
-
# uploaded_file = st.file_uploader("Choose a file")
|
40 |
-
# if uploaded_file is not None:
|
41 |
-
|
42 |
-
data = create_data()
|
43 |
-
unique_cities = data['City'].unique()
|
44 |
-
|
45 |
-
# Select a city
|
46 |
-
selected_city = st.selectbox('Select a City', unique_cities)
|
47 |
-
|
48 |
-
# Sliders for parameter adjustment
|
49 |
-
trend = st.select_slider('Select Trend', options=['add', 'mul', None])
|
50 |
-
damped_trend = st.checkbox('Damped Trend')
|
51 |
-
seasonal = st.select_slider('Select Seasonal', options=['add', 'mul', None])
|
52 |
-
seasonal_period = st.slider('Seasonal Period', 1, 24, 12)
|
53 |
-
|
54 |
-
# ... [previous code remains the same]
|
55 |
-
|
56 |
-
# Display forecast with current parameters
|
57 |
-
city_data = data[data['City'] == selected_city]['Accident Count']
|
58 |
-
forecast, aic = run_exp_smoothing(city_data, trend, damped_trend, seasonal, seasonal_period)
|
59 |
-
|
60 |
-
if forecast is not None:
|
61 |
-
st.write(f"Best Parameters with AIC: {aic}")
|
62 |
-
st.write(f"Trend: {trend}, Damped Trend: {damped_trend}, Seasonal: {seasonal}, Seasonal Period: {seasonal_period}")
|
63 |
-
|
64 |
-
forecast_index = pd.date_range(start=city_data.index[-1], periods=7, freq='M')[1:]
|
65 |
-
forecast_index = forecast_index.to_period('M') # Convert to period index with monthly frequency
|
66 |
-
forecast_df = pd.DataFrame(forecast, index=forecast_index, columns=['Forecast'])
|
67 |
-
|
68 |
-
# Ensure the index is correctly formatted as 'YYYY-MM'
|
69 |
-
forecast_df.index = forecast_df.index.strftime('%Y-%m')
|
70 |
-
|
71 |
-
st.line_chart(forecast_df)
|
72 |
-
|
73 |
-
# ... [rest of the code]
|
74 |
-
|
75 |
-
|
76 |
-
# Grid search button
|
77 |
-
if st.button('Run Grid Search'):
|
78 |
-
best_aic = float('inf')
|
79 |
-
best_params = None
|
80 |
-
for param_set in product(['add', 'mul', None], [True, False], ['add', 'mul', None], [12]):
|
81 |
-
_, temp_aic = run_exp_smoothing(city_data, *param_set)
|
82 |
-
if temp_aic and temp_aic < best_aic:
|
83 |
-
best_aic = temp_aic
|
84 |
-
best_params = param_set
|
85 |
-
st.write(f"Best Parameters: {best_params} with AIC: {best_aic}")
|
86 |
|
87 |
-
#
|
88 |
-
|
89 |
-
|
90 |
-
# excel_data = to_excel(df_to_export)
|
91 |
-
# st.download_button(label='📥 Download Excel', data=excel_data, file_name='forecast.xlsx', mime='application/vnd.ms-excel')
|
92 |
|
|
|
|
|
93 |
|
|
|
|
|
|
|
|
1 |
import pandas as pd
|
2 |
+
import streamlit as st
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
+
# Generate some test data
|
5 |
+
test_index = pd.date_range(start='2023-01-01', periods=6, freq='M')
|
6 |
+
test_data = pd.Series([100, 120, 130, 125, 140, 150], index=test_index)
|
|
|
|
|
7 |
|
8 |
+
# Create a DataFrame
|
9 |
+
test_df = pd.DataFrame(test_data, columns=['Test Forecast'])
|
10 |
|
11 |
+
# Plot the test data
|
12 |
+
st.line_chart(test_df)
|