Improving csv -> dataframe module

[predictops.git] / main.py

diff --git a/main.py b/main.py
index b43c188627d52c218cb527d5dce3ee16dde1575d..a42ce0f11cb9b42feae17fa17e1abcdf513b8570 100644 (file)
--- a/main.py
+++ b/main.py
@@ -1,8 +1,9 @@
 from predictops.source.ephemeris import Ephemeris
 from predictops.source.meteofrance import MeteoFrance
 from predictops.source.ephemeris import Ephemeris
 from predictops.source.meteofrance import MeteoFrance

+from predictops.learn.preprocessing import Preprocessing

 from predictops.target.toarea import ToArea
 
 from predictops.target.toarea import ToArea
 

-from datetime import datetime
+from datetime import datetime, timedelta

 from logging import getLogger
 from logging.config import fileConfig
 from pathlib import Path
 from logging import getLogger
 from logging.config import fileConfig
 from pathlib import Path


@@ -16,7 +17,6 @@ logger = getLogger()
 
 class Engine:
     def __init__(self, start = None, end = None, time_step = None):
 
 class Engine:
     def __init__(self, start = None, end = None, time_step = None):

-        logger.info("Predictops engine launched")

         self._X = {}
         self._Y = {}
 
         self._X = {}
         self._Y = {}
 


@@ -55,7 +55,7 @@ class Engine:
         self._X = x
 
 
         self._X = x
 
 

-start = datetime.strptime('01/01/2010 00:00:00', '%m/%d/%Y %H:%M:%S')
+start = datetime.strptime('01/01/2010 01:00:00', '%m/%d/%Y %H:%M:%S')

 end = datetime.strptime('12/31/2010 23:00:00', '%m/%d/%Y %H:%M:%S')
 
 engine = Engine()
 end = datetime.strptime('12/31/2010 23:00:00', '%m/%d/%Y %H:%M:%S')
 
 engine = Engine()


@@ -64,16 +64,26 @@ engine.add_feature(name = 'meteofrance',
                    latitude = 47.25, longitude = 6.0333, nb_stations = 3,
                    features = ['temperature', 'pressure'])
 
                    latitude = 47.25, longitude = 6.0333, nb_stations = 3,
                    features = ['temperature', 'pressure'])
 

+

 engine.add_feature(name = 'ephemeris',
                    start = start, end = end,
                    features = ['hour', 'dayInWeek', 'dayInMonth', 'dayInYear',
                                'weekInYear', 'month', 'year'])
 
 engine.add_feature(name = 'ephemeris',
                    start = start, end = end,
                    features = ['hour', 'dayInWeek', 'dayInMonth', 'dayInYear',
                                'weekInYear', 'month', 'year'])
 

-print(engine.X[datetime.strptime('06/30/2010 21:00:00', '%m/%d/%Y %H:%M:%S')])
+
+process = Preprocessing(dict_features = engine.X,
+                   start = start, end = end, timestep = timedelta(hours=6))
+
+
+df = process.dataframe.head(n=20)
+#print(engine.X[datetime.strptime('06/30/2010 21:00:00', '%m/%d/%Y %H:%M:%S')])
+print(df)
+exit()

 
 depts = gpd.read_file( Path.cwd() / 'data' / 'targets' / 'departments' / "departements-20180101.shp")
 Doubs = depts.loc[depts['nom'] == 'Doubs'].iloc[0]
 
 ToArea(area=Doubs.geometry,
 
 depts = gpd.read_file( Path.cwd() / 'data' / 'targets' / 'departments' / "departements-20180101.shp")
 Doubs = depts.loc[depts['nom'] == 'Doubs'].iloc[0]
 
 ToArea(area=Doubs.geometry,

-       start = start, end = end)
+       start = start, end = end,
+       csv_file = Path.cwd() / 'data' / 'targets' / 'sdis25' / 'interventions.csv')