def main():
# Data Extraction
df = data_extract_e('e_20190609_15.pkl')
# Data Transformation and Engineering
df = feature_eng(df)
df = extract_queues(df)
dept_encoder, queue_encoder = load_labels('dept_encoder.pkl',
'queue_encoder.pkl',
df=df)
df = feature_transform(df,
dept_encoder=dept_encoder,
queue_encoder=queue_encoder)
# Training/Test Split
x, y = data_filter(df)
x_train, x_test, y_train, y_test = train_test_split(
x, y, test_size=0.2,
random_state=1357) # 2468 to use same shuffle as individual models
# Load models from persistent files
models = load_models()
print(models)
# Stacking
# Produces a new set of features based on the predictions of base models
x_train_s, x_test_s = stacking(models,
x_train,
y_train,
x_test,
n_folds=10,
shuffle=True,
verbose=0,
regression=True)
save_data(x_train_s, 'x_train_s.pkl')
save_data(y_train, 'y_train.pkl')
save_data(x_test_s, 'x_test_s.pkl')
save_data(y_test, 'y_test.pkl')
import pandas as pd
import numpy as np
from ai_cloud_etl import data_extract_e, data_filter, feature_eng, feature_transform, extract_queues, fit_labels
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score
from tpot import TPOTRegressor
import xgb_config
# Data Extraction
df = data_extract_e('e_20190609_15.pkl')
# Data Transformation and Engineering
df = feature_eng(df)
df = extract_queues(df)
dept_encoder, queue_encoder = fit_labels(df)
df = feature_transform(df, queue_encoder, dept_encoder)
# Training/Test Split
x, y = data_filter(df)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=2468)
# Using TPOT AutoML
tpot = TPOTRegressor(n_jobs=-1,
verbosity=1,
config_dict=xgb_config.xgb_config_dict)
tpot = tpot.fit(x_train, y_train)
y_pred = tpot.predict(x_train)
print('XGB TPOT training R2 score: ', r2_score(y_train, y_pred))