def split_table_by_number(xlsTable,
row_number,
output,
sheetName=None,
sheetIndex=None):
"""
Split a table by row number
Given a number of rows, this method will split an input table
in several tables with a number of rows equal to row_number.
TODO: Do it with Pandas
"""
import xlrd
import xlwt
from gasp.mng.fld.xls import columns_by_order
from gasp.fm import tbl_to_obj
COLUMNS_ORDER = columns_by_order(xlsTable,
sheet_name=sheetName,
sheet_index=sheetIndex)
DATA = tbl_to_obj(xlsTable,
sheet=sheetIndex if sheetIndex else sheetName,
output='array')
# Create output
out_xls = xlwt.Workbook()
l = 1
s = 1
base = sheetName if sheetName else 'data'
for row in DATA:
if l == 1:
sheet = out_xls.add_sheet('{}_{}'.format(base, s))
# Write Columns
for col in range(len(COLUMNS_ORDER)):
sheet.write(0, col, COLUMNS_ORDER[col])
for col in range(len(COLUMNS_ORDER)):
sheet.write(l, col, row[COLUMNS_ORDER[col]])
l += 1
if l == row_number + 1:
l = 1
s += 1
# Save result
out_xls.save(output)
def merge_feat(shps, outShp, api="ogr2ogr"):
"""
Get all features in several Shapefiles and save them in one file
"""
if api == "ogr2ogr":
from gasp import exec_cmd
from gasp.prop.ff import drv_name
out_drv = drv_name(outShp)
# Create output and copy some features of one layer (first in shps)
cmdout = exec_cmd('ogr2ogr -f "{}" {} {}'.format(
out_drv, outShp, shps[0]
))
# Append remaining layers
lcmd = [exec_cmd(
'ogr2ogr -f "{}" -update -append {} {}'.format(
out_drv, outShp, shps[i]
)
) for i in range(1, len(shps))]
elif api == 'pandas':
"""
Merge SHP using pandas
"""
from gasp.fm import tbl_to_obj
from gasp.to.shp import df_to_shp
if type(shps) != list:
raise ValueError('shps should be a list with paths for Feature Classes')
dfs = [tbl_to_obj(shp) for shp in shps]
result = dfs[0]
for df in dfs[1:]:
result = result.append(df, ignore_index=True, sort=True)
df_to_shp(result, outShp)
else:
raise ValueError(
"{} API is not available"
)
return outShp
def tbl_to_tbl(inTbl,
outTbl,
inSheet=None,
txtDelimiter=None,
inTxtDelimiter=None,
inEncoding='utf-8'):
"""
Convert data format
"""
from gasp.fm import tbl_to_obj
data = tbl_to_obj(inTbl,
sheet=inSheet,
encoding_=inEncoding,
_delimiter=inTxtDelimiter)
outTbl = obj_to_tbl(data, outTbl, delimiter=txtDelimiter)
return outTbl
def predict_fm_mdl(mdlFile, vFile, data, txtCol, method='NaiveBayes'):
"""
Text classification using file with fit data
"""
from joblib import load
import pandas as pd
from gasp.fm import tbl_to_obj
classDf = tbl_to_obj(data) if type(data) != pd.DataFrame else data
classDf = classDf[pd.notnull(classDf[txtCol])]
clf = load(mdlFile)
tvect = None if not vFile else load(vFile)
if method == 'NaiveBayes':
result = clf.predict(tvect.transform(data[txtCol]))
data.loc[:, 'classification'] = result
elif method == 'LinearSupportVectorMachine':
feaTst = tvect.transform(classDf[txtCol])
y_pred = clf.predict(feaTst)
data.loc[:, 'classification'] = y_pred
elif method == 'RandomForest':
feaTst = tvect.transform(classDf[txtCol])
y_pred=clf.predict(feaTst)
data.loc[:, 'classification'] = y_pred
elif method == 'LogisticRegression':
y_pred = clf.predict(classDf[txtCol])
data.loc[:, 'classification'] = y_pred
return data
def same_attr_to_shp(inShps, interestCol, outFolder, basename="data_",
resultDict=None):
"""
For several SHPS with the same field, this program will list
all values in such field and will create a new shp for all
values with the respective geometry regardeless the origin shp.
"""
import os
from gasp import goToList
from gasp.fm import tbl_to_obj
from gasp.mng.gen import merge_df
from gasp.to.shp import df_to_shp
EXT = os.path.splitext(inShps[0])[1]
shpDfs = [tbl_to_obj(shp) for shp in inShps]
DF = merge_df(shpDfs, ignIndex=True)
#DF.dropna(axis=0, how='any', inplace=True)
uniqueVal = DF[interestCol].unique()
nShps = [] if not resultDict else {}
for val in uniqueVal:
ndf = DF[DF[interestCol] == val]
KEY = str(val).split('.')[0] if '.' in str(val) else str(val)
nshp = df_to_shp(ndf, os.path.join(
outFolder, '{}{}{}'.format(basename, KEY, EXT)
))
if not resultDict:
nShps.append(nshp)
else:
nShps[KEY] = nshp
return nShps
