# -*- coding: utf-8 -*-
# Filters: individuals at least one time in the corps
from __future__ import division
import os
import pandas as pd
import numpy as np
from fonction_publique.base import raw_directory_path, get_careers, parser
from slugify import slugify
import matplotlib.pyplot as plt
fig_save_path = "C:/Users/l.degalle/CNRACL/fonction-publique/fonction_publique/ecrits/note_1_Lisa/Figures"
libelles_emploi_directory = parser.get('correspondances',
'libelles_emploi_directory')
save_path = 'M:/CNRACL/output'
data_AT = pd.read_csv(
os.path.join(save_path,"corps_AT_2011_w_echelon_conditions.csv")
)
data_AT_echelon_2011_T1 = data_AT.query(
'(annee == 2011) & (trimestre == 1)'
)[['ident', 'echelon_y']]
data_AT_without_1st_transition = data_AT[
~data_AT['ident'].isin(data_AT_echelon_2011_T1['ident'].tolist()) &
data_AT['echelon_y'].isin(
data_AT_echelon_2011_T1['echelon_y'].tolist()
)]
from __future__ import division
import logging
import os
import pandas as pd
import numpy as np
import sys
from fonction_publique.matching_grade.grade_matching import get_correspondance_data_frame
from fonction_publique.merge_careers_and_legislation import get_grilles
from fonction_publique.base import parser
from fonction_publique.matching_grade.grade_matching import validate_correspondance
log = logging.getLogger(__name__)
libelles_emploi_directory = parser.get('correspondances',
'libelles_emploi_directory')
output_directory = parser.get('data', 'output')
def main():
correspondance_data_frame = get_correspondance_data_frame(which='grade')
valid_data_frame = validate_correspondance(correspondance_data_frame,
check_only=True)
assert valid_data_frame, 'The correspondace data frame is not valid'
grilles = get_grilles()
grilles.loc[grilles.libelle_grade_NEG == 'INFIRMIER DE CLASSE NORMALE (*)',
'libelle_grade_NEG'] = 'INFIRMIER DE CLASSE NORMALE(*)'
grilles.loc[grilles.libelle_grade_NEG ==
'INFIRMIER DE CLASSE SUPERIEURE (*)',
'libelle_grade_NEG'] = 'INFIRMIER DE CLASSE SUPERIEURE(*)'
import sys
import numpy as np
import pandas as pd
from slugify import slugify
from fuzzywuzzy import process
from fonction_publique.base import get_careers, parser, LIBELLES_MAX_ROWS
from fonction_publique.merge_careers_and_legislation import get_grilles
log = logging.getLogger(__name__)
DEBUG = False
VERSANTS = ['T', 'H']
correspondance_data_frame_path = parser.get('correspondances', 'h5')
corps_correspondance_data_frame_path = parser.get('correspondances',
'corps_h5')
libelles_emploi_directory = parser.get('correspondances',
'libelles_emploi_directory')
def get_correspondance_data_frame(which=None, netneh=False):
"""
Charge la table avec les libellés déjà classés.
Returns
-------
data_frame : table de correspondance (chargée, ou nouvelle générée)
"""
assert which in ['grade', 'corps'
#!/usr/bin/env python
# -*- coding:utf-8 -*-
from __future__ import division
import logging
import pandas as pd
from fonction_publique.base import parser
from fonction_publique.matching_grade.grade_matching import select_grade_neg
log = logging.getLogger(__name__)
correspondance_data_frame_path = parser.get('correspondances', 'h5')
#correspondance_1 = pd.read_hdf(correspondance_data_frame_path, 'correspondance')
#try:
# correspondance_2 = pd.read_hdf('C:/Users/s.rabate/Downloads/correspondances.h5', 'correspondance')
#except:
# correspondance_2 = pd.read_hdf('/Users/simonrabate/Downloads/correspondances.h5', 'correspondance')
def validate_tables_to_merge(correspondance_data_frame1, correspondance_data_frame2):
# 1. conflicting_entries
df = correspondance_data_frame1.merge(
correspondance_data_frame2,
how = 'inner',
on = ['versant', 'libelle', 'annee']