In [1]:
import pandas as pd
import numpy as np
import pickle
import os
root_directory = 'D:/github/w_vattenstatus/ekostat_calculator'#"../" #os.getcwd()
workspace_directory = root_directory + '/workspaces'
resource_directory = root_directory + '/resources'
#alias = 'lena'
user_id = 'test_user' #kanske ska vara off_line user?
workspace_alias = 'lena_indicator' # kustzonsmodellen_3daydata
# workspace_alias = 'kustzonsmodellen_3daydata'
# ## Initiate EventHandler
print(root_directory)
paths = {'user_id': user_id,
'workspace_directory': root_directory + '/workspaces',
'resource_directory': root_directory + '/resources',
'log_directory': 'D:/github' + '/log',
'test_data_directory': 'D:/github' + '/test_data',
'cache_directory': 'D:/github/w_vattenstatus/cache'}
In [17]:
sharkweb_matchfile = pd.read_csv(open(paths['resource_directory']+'/mappings/water_body_match_sharweb_SVAR_2012_2.txt'), sep = '\t')
In [3]:
current_matchfile = pd.read_csv(open(paths['resource_directory']+'/mappings/water_body_match.txt'), sep = '\t')
current_matchfile_new = pd.read_csv(open(paths['resource_directory']+'/mappings/water_body_match_new.txt'), sep = '\t')
In [35]:
ix_12s = sharkweb_matchfile.loc[sharkweb_matchfile['TYPE_AREA_CODE'] == '12s'].index
ix_12n = sharkweb_matchfile.loc[sharkweb_matchfile['TYPE_AREA_CODE'] == '12n'].index
ix_1s = sharkweb_matchfile.loc[sharkweb_matchfile['TYPE_AREA_CODE'] == '1s'].index
ix_1n = sharkweb_matchfile.loc[sharkweb_matchfile['TYPE_AREA_CODE'] == '1n'].index
sharkweb_matchfile['TYPE_AREA_SUFFIX'] = ''
sharkweb_matchfile.loc[ix_1n, 'TYPE_AREA_SUFFIX'] = 'n'
sharkweb_matchfile.loc[ix_12n, 'TYPE_AREA_SUFFIX'] = 'n'
sharkweb_matchfile.loc[ix_1s, 'TYPE_AREA_SUFFIX'] = 's'
sharkweb_matchfile.loc[ix_12s, 'TYPE_AREA_SUFFIX'] = 's'
In [38]:
sharkweb_matchfile['TYPE_AREA_NAME'] = ''
for type_code in sharkweb_matchfile.TYPE_AREA_CODE.unique():
ix = sharkweb_matchfile.loc[sharkweb_matchfile['TYPE_AREA_CODE'] == type_code].index
type_code_new = current_matchfile.loc[current_matchfile.TYPE_AREA_CODE == type_code].TYPE_AREA_CODE.unique()
type_suffix_new = current_matchfile.loc[current_matchfile.TYPE_AREA_CODE == type_code].TYPE_AREA_SUFFIX.unique()
type_name_new = current_matchfile.loc[current_matchfile.TYPE_AREA_CODE == type_code].TYPE_AREA_NAME.unique()
type_suffix = sharkweb_matchfile.loc[sharkweb_matchfile.TYPE_AREA_CODE == type_code].TYPE_AREA_SUFFIX.unique()
print(type_code, type_suffix_new, type_code_new, type_suffix, type_name_new)
try:
sharkweb_matchfile.loc[ix, 'TYPE_AREA_NAME'] = type_name_new[0]
except IndexError as e:
print(type_code, e)
In [39]:
sharkweb_matchfile.to_csv(paths['resource_directory']+'/mappings/water_body_match_sharkweb_SVAR_2012_2_extended_new.txt', sep = '\t')
In [4]:
missing_wb = pd.read_csv(open('D:\github\w_vattenstatus\dokumentation\HID_not_matching_VISS_EU_CD_SVAR_2012_2.txt'), sep = '\t')
missing_wb.head()
Out[4]:
In [29]:
ix_list = []
for HID in missing_wb.HID:
ix = sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')].index
print('HID: {} in SVAR2012 file used as VISS_EU_CD in sharkweb'.format(HID.strip('SE')))
ix_list.append(sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')].index[0])
print(sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')][['WATER_BODY_NAME','HID','VISS_EU_CD']])
#print(sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')][['WATER_BODY_NAME']].values[0])
#print(sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')][['HID']].values[0])
#print(sharkweb_matchfile.loc[sharkweb_matchfile['HID'] == HID.strip('SE')][['VISS_EU_CD']].values[0])
In [40]:
#to_save = sharkweb_matchfile.loc[sharkweb_matchfile.index[ix_list]].copy()
sharkweb_matchfile.loc[sharkweb_matchfile.index[ix_list]].to_csv('D:/github/w_vattenstatus/dokumentation/VISS_EU_CD_missmatch_with_HID.txt', sep = '\t')
In [61]:
sharkweb_matchfile.to_csv(paths['resource_directory']+'/mappings/water_body_match_sharkweb_SVAR_2012_2_extended_changed_HID_to_EU_CD.txt', sep = '\t')
In [13]:
current_matchfile.head()
Out[13]:
In [12]:
current_matchfile.columns
Out[12]:
In [36]:
sharkweb_matchfile.head()
Out[36]:
In [17]:
Out[17]:
In [2]:
', '.join(['a','b','c'])
Out[2]:
In [5]:
sharkweb_matchfile.head()
Out[5]:
In [41]:
new_df = pd.DataFrame()
new_df2 = new_df.append(pd.DataFrame(data = [[4,6]], index = [9], columns = ['A','B']))
new_df2 = new_df2.append(pd.DataFrame(data = [[8,10]], index = [5], columns = ['A','B']))
In [39]:
new_df2.head()
Out[39]:
In [42]:
new_df = pd.DataFrame()
new_df3 = new_df.append(pd.DataFrame(data = [[4,6]], index = [9], columns = ['C','D']))
new_df3 = new_df3.append(pd.DataFrame(data = [[8,10]], index = [5], columns = ['C','D']))
In [59]:
new_df2.merge(new_df3, left_index = True, right_index = True).ix[[9,5]]
Out[59]:
In [ ]:
In [53]:
sharkweb_matchfile.loc[sharkweb_matchfile.index[[4,8,3,21]]]
In [ ]:
In [ ]: