from configparser import ConfigParser
+from logging import getLogger
+from logging.config import fileConfig
from math import sqrt
+from pathlib import Path
from sklearn.metrics import mean_squared_error, mean_absolute_error
from sklearn.model_selection import train_test_split
+from statistics import mean, stdev
+import lightgbm as lgb
+import matplotlib
+import os
+import pandas as pd
+import pylab as P
import xgboost
+fileConfig((Path.cwd() / 'config') / 'logging.cfg')
+logger = getLogger()
+
+
class Learning:
- def __init__(self, config_file = None,
- X = None, y = None):
+ def __init__(self, config_file=None, file_name=None,
+ X=None, y=None, horizon=0):
self._config = ConfigParser()
self._config.read(config_file)
+ self._file_name = file_name
+ logger.info("Dealing with the horizon of prediction")
+ if horizon:
+ self._X = X[:-horizon]
+ self._y = y[horizon:]
+ else:
+ self._X = X
+ self._y = y
+ rep = (Path.cwd() / self._file_name)
+ rep.mkdir()
+ self._filename = str(self._file_name / os.path.basename(self._file_name))
+ self._X.to_csv(self._filename + '.csv')
+ self._learn()
+ self._evaluate()
- df = X
- df['cible'] = y
-
- print(df.head())
-
- train_val_set, test_set = train_test_split(df, test_size = 0.2, random_state = 42)
- train_set, val_set = train_test_split(train_val_set, test_size = 0.2, random_state = 42)
+ def _learn(self):
+ logger.info("Generation of learning sets")
+ self._df = self._X
+ self._df['cible'] = self._y
+ train_val_set, test_set = train_test_split(self._df, test_size=0.2, random_state=42)
+ train_set, val_set = train_test_split(train_val_set, test_size=0.2, random_state=42)
- X_test = test_set.drop('cible', axis = 1)
- y_test = test_set['cible'].copy()
+ self._X_test = test_set.drop('cible', axis=1)
+ self._y_test = test_set['cible'].copy()
X_train = train_set.drop('cible', axis=1)
y_train = train_set['cible'].copy()
X_val = val_set.drop('cible', axis=1)
y_val = val_set['cible'].copy()
+ logger.info("Start learning")
+ if self._config['MODEL']['method'] == 'xgboost':
+ logger.info("Using xgboost regressor")
+ self._reg = xgboost.XGBRegressor(learning_rate=self._config['HYPERPARAMETERS'].getfloat('learning_rate'),
+ max_depth=self._config['HYPERPARAMETERS'].getint('max_depth'),
+ random_state=self._config['HYPERPARAMETERS'].getint('random_state'),
+ n_estimators=self._config['HYPERPARAMETERS'].getint('n_estimators'),
+ n_jobs=self._config['HYPERPARAMETERS'].getint('n_jobs'),
+ objective='count:poisson')
+
+ self._reg.fit(X_train, y_train,
+ eval_set=[(X_val, y_val)],
+ early_stopping_rounds=10)
+ elif self._config['MODEL']['method'] == 'lightgbm':
+ train_data = lgb.Dataset(X_train, label=y_train)
+ val_data = lgb.Dataset(X_val, label=y_val)
+ num_round = self._config['HYPERPARAMETERS'].getint('num_round')
+ param = {
+ 'learning_rate': self._config['HYPERPARAMETERS'].getfloat('learning_rate'),
+ 'metric': self._config['HYPERPARAMETERS'].get('metric'),
+ 'num_iterations': self._config['HYPERPARAMETERS'].getint('num_iterations'),
+ 'num_leaves': self._config['HYPERPARAMETERS'].getint('num_leaves'),
+ 'objective': self._config['HYPERPARAMETERS'].get('objective')
+ }
+ self._reg = lgb.train(param, train_data, num_round, valid_sets=[val_data])
+
+ def _evaluate(self):
+ logger.info("Evaluation of the learner")
+ y_test_pred = self._reg.predict(self._X_test)
+ txt = f"Average interventions per time unit: {mean(self._df.cible)}\n"
+ txt += f"Standard deviation: {stdev(self._df.cible)}\n\n"
+
+ txt += f"Mean absolute error: {mean_absolute_error(y_test_pred, self._y_test)}\n"
+ txt += f"Root mean squared error: {sqrt(mean_squared_error(y_test_pred, self._y_test))}\n\n"
+
+ for k in range(10):
+ txt += f"Percentage of errors lower than {k}: {[abs(int(u-v))<=k for u,v in zip(self._y_test.values, y_test_pred)].count(True)/len(self._y_test)*100}\n"
+
+ print(txt)
+ with open(self._filename + ".result", 'w') as f:
+ f.write(txt)
+
+ y_true = self._df[self._df.year == self._df.year.max()].cible
+ x_true = self._df[self._df.year == self._df.year.max()].drop('cible', axis=1)
+
+ yy_test_pred = self._reg.predict(x_true)
+ P.figure(figsize=(36, 16))
+ P.plot(list(y_true)[:300], color='blue', label='actual')
+ P.plot(yy_test_pred[:300], color='red', label='predicted')
+ P.title('Predictions for 2018')
+ P.xlabel('Hour in the year')
+ P.ylabel('Number of cumulated interventions')
+ P.legend()
+ P.savefig(self._filename + ".png")
+
+ yy_test_pred = self._reg.predict(self._X_test)
+ P.figure(figsize=(36, 16))
+ P.plot(list(self._y_test)[:300], color='blue', label='actual')
+ P.plot(yy_test_pred[:300], color='red', label='predicted')
+ P.title('Predictions for test set')
+ P.xlabel('Hour in the year')
+ P.ylabel('Number of cumulated interventions')
+ P.legend()
+ P.savefig(self._filename + "-test.png")
if self._config['MODEL']['method'] == 'xgboost':
- xgb_reg = xgboost.XGBRegressor(learning_rate = 0.01,
- max_depth = 10,
- random_state=42,
- n_estimators = 173,
- n_jobs=-1,
- objective = 'count:poisson')
-
- xgb_reg.fit(X_train, y_train,
- eval_set=[(X_val, y_val)],
- early_stopping_rounds=10)
-
- y_test_pred = xgb_reg.predict(X_test)
- print(sqrt(mean_squared_error(y_test_pred, y_test)), mean_absolute_error(y_test_pred,y_test))
\ No newline at end of file
+ xgboost.plot_importance(self._reg)
+ fig = matplotlib.pyplot.gcf()
+ fig.set_size_inches(15, 130)
+ fig.savefig(self._filename + '-feat_importance.pdf')
