Refactoring, fin du lever/coucher de soleil, et début de sentinelles

[predictops.git] / predictops / learn / learning.py

diff --git a/predictops/learn/learning.py b/predictops/learn/learning.py
index 959271ded77ad22aea436d98632ab7e97cf272d4..f13c3a6514eb2a8b552a4aa80fd13b275f590036 100644 (file)
--- a/predictops/learn/learning.py
+++ b/predictops/learn/learning.py
@@ -10,6 +10,7 @@ from statistics import mean, stdev
 import lightgbm as lgb
 import matplotlib
 import os
 import lightgbm as lgb
 import matplotlib
 import os

+import pandas as pd

 import pylab as P
 import xgboost
 
 import pylab as P
 import xgboost
 


@@ -25,8 +26,12 @@ class Learning:
         self._config.read(config_file)
         self._file_name = file_name
         logger.info("Dealing with the horizon of prediction")
         self._config.read(config_file)
         self._file_name = file_name
         logger.info("Dealing with the horizon of prediction")

-        self._X = X[:-horizon]
-        self._y = y[horizon:]
+        if horizon:
+            self._X = X[:-horizon]
+            self._y = y[horizon:]
+        else:
+            self._X = X
+            self._y = y

         self._learn()
         self._evaluate()
 
         self._learn()
         self._evaluate()
 


@@ -83,11 +88,12 @@ class Learning:
         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"
 
         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)

         rep = (Path.cwd() / self._file_name)
         rep.mkdir()
         rep = (Path.cwd() / self._file_name)
         rep.mkdir()

-        filename = str(self._file_name / os.path.basename(self._file_name))
-        with open(filename + ".result", 'w') as f:
+        self._filename = str(self._file_name / os.path.basename(self._file_name))
+
+        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
             f.write(txt)
 
         y_true = self._df[self._df.year == self._df.year.max()].cible


@@ -101,7 +107,7 @@ class Learning:
         P.xlabel('Hour in the year')
         P.ylabel('Number of cumulated interventions')
         P.legend()
         P.xlabel('Hour in the year')
         P.ylabel('Number of cumulated interventions')
         P.legend()

-        P.savefig(filename + ".png")
+        P.savefig(self._filename + ".png")

 
         yy_test_pred = self._reg.predict(self._X_test)
         P.figure(figsize=(36, 16))
 
         yy_test_pred = self._reg.predict(self._X_test)
         P.figure(figsize=(36, 16))


@@ -111,10 +117,10 @@ class Learning:
         P.xlabel('Hour in the year')
         P.ylabel('Number of cumulated interventions')
         P.legend()
         P.xlabel('Hour in the year')
         P.ylabel('Number of cumulated interventions')
         P.legend()

-        P.savefig(filename + "-test.png")
+        P.savefig(self._filename + "-test.png")

 
         if self._config['MODEL']['method'] == 'xgboost':
             xgboost.plot_importance(self._reg)
             fig = matplotlib.pyplot.gcf()
             fig.set_size_inches(15, 130)
 
         if self._config['MODEL']['method'] == 'xgboost':
             xgboost.plot_importance(self._reg)
             fig = matplotlib.pyplot.gcf()
             fig.set_size_inches(15, 130)

-            fig.savefig(filename + '-feat_importance.pdf')
+            fig.savefig(self._filename + '-feat_importance.pdf')