/ EXERCISE

Time Series Forecasting with PyCaret Regression Module

Time Series Forecasting with PyCaret Regression Module

Imports

import pandas as pd
import numpy as np

from pycaret.regression import *
import plotly.express as px

Data

data = pd.read_csv('../exercise/data/airline_passengers.csv')
cols = ['Date','Passengers']
data.columns = cols
data['Date'] = pd.to_datetime(data['Date'])

data['Month'] = [i.month for i in data['Date']]
data['Year'] = [i.year for i in data['Date']]

data['Series'] = np.arange(1, len(data)+1)

data.drop(['Date'], axis=1, inplace=True)
data = data[['Series','Year','Month','Passengers']]

data.head()
Series Year Month Passengers
0 1 1949 1 112
1 2 1949 2 118
2 3 1949 3 132
3 4 1949 4 129
4 5 1949 5 121 
train = data[data['Year'] < 1960]
test = data[data['Year'] >= 1960]

print(train.shape, test.shape)

(132, 4) (12, 4)

Setup

s = setup(data = train, test_data= test, target='Passengers', fold_strategy='timeseries',numeric_features=['Year','Series'],
         fold=3, transform_target= True, session_id=1234)
Description Value
0 session_id 1234
1 Target Passengers
2 Original Data (132, 4)
3 Missing Values False
4 Numeric Features 2
5 Categorical Features 1
6 Ordinal Features False
7 High Cardinality Features False
8 High Cardinality Method None
9 Transformed Train Set (132, 13)
10 Transformed Test Set (12, 13)
11 Shuffle Train-Test True
12 Stratify Train-Test False
13 Fold Generator TimeSeriesSplit
14 Fold Number 3
15 CPU Jobs -1
16 Use GPU False
17 Log Experiment False
18 Experiment Name reg-default-name
19 USI 420a
20 Imputation Type simple
21 Iterative Imputation Iteration None
22 Numeric Imputer mean
23 Iterative Imputation Numeric Model None
24 Categorical Imputer constant
25 Iterative Imputation Categorical Model None
26 Unknown Categoricals Handling least_frequent
27 Normalize False
28 Normalize Method None
29 Transformation False
30 Transformation Method None
31 PCA False
32 PCA Method None
33 PCA Components None
34 Ignore Low Variance False
35 Combine Rare Levels False
36 Rare Level Threshold None
37 Numeric Binning False
38 Remove Outliers False
39 Outliers Threshold None
40 Remove Multicollinearity False
41 Multicollinearity Threshold None
42 Remove Perfect Collinearity True
43 Clustering False
44 Clustering Iteration None
45 Polynomial Features False
46 Polynomial Degree None
47 Trignometry Features False
48 Polynomial Threshold None
49 Group Features False
50 Feature Selection False
51 Feature Selection Method classic
52 Features Selection Threshold None
53 Feature Interaction False
54 Feature Ratio False
55 Interaction Threshold None
56 Transform Target True
57 Transform Target Method box-cox

Train and Evaluation all Models

best = compare_models(sort='MAE')
Model MAE MSE RMSE R2 RMSLE MAPE TT (Sec)
lar Least Angle Regression 22.3980 923.8646 28.2855 0.5621 0.0878 0.0746 0.0100
lr Linear Regression 22.3981 923.8726 28.2856 0.5621 0.0878 0.0746 0.7533
huber Huber Regressor 22.4145 890.8041 27.9201 0.5996 0.0879 0.0749 0.0133
br Bayesian Ridge 22.4783 932.2165 28.5483 0.5611 0.0884 0.0746 0.0067
ridge Ridge Regression 23.1976 1003.9426 30.0410 0.5258 0.0933 0.0764 0.5433
lasso Lasso Regression 38.4188 2413.5112 46.8468 0.0882 0.1473 0.1241 0.5833
en Elastic Net 40.6486 2618.8760 49.4048 -0.0824 0.1563 0.1349 0.6100
omp Orthogonal Matching Pursuit 44.3054 3048.2658 53.8613 -0.4499 0.1713 0.1520 0.0100
xgboost Extreme Gradient Boosting 46.7192 3791.0476 59.9683 -0.5515 0.1962 0.1432 0.0900
gbr Gradient Boosting Regressor 50.1533 3999.2462 60.8044 -0.5727 0.2006 0.1532 0.0133
rf Random Forest Regressor 50.5690 4353.5509 63.1335 -0.6559 0.2049 0.1522 0.1667
par Passive Aggressive Regressor 54.4213 5240.3837 65.8810 -0.6782 0.2058 0.1599 0.0100
et Extra Trees Regressor 55.3698 4586.5516 64.8302 -0.7724 0.2189 0.1708 0.1700
dt Decision Tree Regressor 56.7172 5950.5556 69.7680 -0.8908 0.2224 0.1670 0.0100
ada AdaBoost Regressor 58.5851 5701.3655 72.0880 -1.1245 0.2377 0.1757 0.0233
knn K Neighbors Regressor 64.1165 7098.4735 78.7031 -1.4511 0.2582 0.1882 0.0433
lightgbm Light Gradient Boosting Machine 76.8521 8430.4943 91.0063 -2.9097 0.3379 0.2490 0.0133
llar Lasso Least Angle Regression 129.0182 21858.5806 138.1309 -6.5554 0.5446 0.3958 0.0100 
prediction_holdout = predict_model(best)
Model MAE MSE RMSE R2 RMSLE MAPE
0 Least Angle Regression 25.0714 972.2733 31.1813 0.8245 0.0692 0.0571 
predictions = predict_model(best, data=data)
predictions['Date'] = pd.date_range(start='1949-01-01', end='1960-12-01', freq='MS')

fig = px.line(predictions, x='Date',y=['Passengers','Label'], template='plotly_dark')
fig.add_vrect(x0='1960-01-01', x1='1960-12-01', fillcolor='grey',opacity=.25, line_width=0)
fig.show()

image1

final_best = finalize_model(best)

Forecast

future_dates = pd.date_range(start = '1961-01-01', end = '1965-01-01', freq = 'MS')
future_df = pd.DataFrame()
future_df['Month'] = [i.month for i in future_dates]
future_df['Year'] = [i.year for i in future_dates]    
future_df['Series'] = np.arange(145, (145 + len(future_dates)))

future_df.head()
Month Year Series
0 1 1961 145
1 2 1961 146
2 3 1961 147
3 4 1961 148
4 5 1961 149 
predictions_future = predict_model(final_best, data=future_df)
predictions_future.head()
Month Year Series Label
0 1 1961 145 486.278267
1 2 1961 146 482.208187
2 3 1961 147 550.485967
3 4 1961 148 535.187177
4 5 1961 149 538.923789 
concat_df = pd.concat([data, predictions_future], axis=0)
concat_df_i = pd.date_range(start='1949-01-01', end='1965-01-01', freq='MS')
concat_df.set_index(concat_df_i, inplace=True)

fig = px.line(concat_df, x=concat_df.index, y=['Passengers', 'Label'], template='plotly_dark')
fig.show()

image2

Reference : Time Series Forecasting with PyCaret Regression Module