def test_reading_through_sheets(self):
b = pe.BookReader(self.testfile)
data = pe.utils.to_array(b["Sheet1"].rows())
expected = [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]]
assert data == expected
data = pe.to_array(b["Sheet2"].rows())
expected = [[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6]]
assert data == expected
data = pe.to_array(b["Sheet3"].rows())
expected = [[u'X', u'Y', u'Z'], [1, 4, 7], [2, 5, 8], [3, 6, 9]]
assert data == expected
sheet3 = b["Sheet3"]
s3 = sheet3.become_series()
data = pe.to_array(s3.rows())
expected = [[1, 4, 7], [2, 5, 8], [3, 6, 9]]
assert data == expected
def test_reading_through_sheets(self):
b = pe.BookReader(self.testfile)
data = pe.utils.to_array(b["Sheet1"].rows())
expected = [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]]
assert data == expected
data = pe.to_array(b["Sheet2"].rows())
expected = [[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6]]
assert data == expected
data = pe.to_array(b["Sheet3"].rows())
expected = [[u'X', u'Y', u'Z'], [1, 4, 7], [2, 5, 8], [3, 6, 9]]
assert data == expected
sheet3 = b["Sheet3"]
sheet3.name_columns_by_row(0)
data = pe.to_array(sheet3.rows())
expected = [[1, 4, 7], [2, 5, 8], [3, 6, 9]]
assert data == expected
def test_empty_series_reader(self):
# debug this further
s = pe.Sheet() # seriesreader is gone since v0.0.7
assert s.name == "pyexcel"
test_data = [[1, 2, 3], [4, 5, 6], ["Column 1", "Column 2", "Column 3"]]
s.column += pe.transpose(test_data)
actual = pe.to_array(s)
assert test_data == actual
s.name_columns_by_row(2)
assert s.colnames == test_data[2]
def test_empty_series_reader(self):
# debug this further
s = pe.Sheet() # seriesreader is gone since v0.0.7
assert s.name == "pyexcel sheet"
test_data = [[1, 2, 3], [4, 5, 6],
["Column 1", "Column 2", "Column 3"]]
s.column += pe.transpose(test_data)
actual = pe.to_array(s)
assert test_data == actual
s.name_columns_by_row(2)
assert s.colnames == test_data[2]
def input_from_excel(): input_sheet = excel.get_sheet(file_name="supers_data.xlsx", name_columns_by_row=0) records = excel.to_array(input_sheet.rows()) for record in records: if not irl_city_exist(record[3]) and record[5] != '' and record[6] != '': new_irl_city = IRLCity.objects.create(name=record[3], province=record[4], latitude=record[5] , longitude=record[6]) new_irl_city.save() if not universe_exist(record[2]): new_bang = Universe.objects.create(company_name=record[2], origin_country=record[8]) new_bang.save() if not super_exist(record[0]): if record[3] != '': city = IRLCity.objects.get(name=record[3]) universe = Universe.objects.get(company_name=record[2]) new_super = Super.objects.create(name=record[0],identity=record[7],origin_city=record[1],irl_city=city, company_universe=universe) new_super.save()
def main(base_dir):
# print all in json
#
# Column 1 Column 2 Column 3
# 1 4 7
# 2 5 8
# 3 6 9
sheet = pe.load(os.path.join(base_dir, "example_series.ods"),
name_columns_by_row=0)
print(json.dumps(sheet.to_dict()))
# output:
# {"Column 2": [4.0, 5.0, 6.0], "Column 3": [7.0, 8.0, 9.0], "Column 1": [1.0, 2.0, 3.0]}
# get the column headers
print(sheet.colnames)
# [u'Column 1', u'Column 2', u'Column 3']
# get the content in one dimensional array
data = pe.to_array(sheet.enumerate())
print(data)
# [1.0, 4.0, 7.0, 2.0, 5.0, 8.0, 3.0, 6.0, 9.0]
# get the content in one dimensional array
# in reverse order
data = pe.to_array(sheet.reverse())
print(data)
# get the content in one dimensional array
# but iterate it vertically
data = pe.to_array(sheet.vertical())
print(data)
# [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
# get the content in one dimensional array
# but iterate it vertically in revserse
# order
data = pe.to_array(sheet.rvertical())
print(data)
#[9.0, 8.0, 7.0, 6.0, 5.0, 4.0, 3.0, 2.0, 1.0]
# get a two dimensional array
data = pe.to_array(sheet.rows())
print(data)
#[[1.0, 4.0, 7.0], [2.0, 5.0, 8.0], [3.0, 6.0, 9.0]]
# get a two dimensional array in reverse
# order
data = pe.to_array(sheet.rrows())
print(data)
# [[3.0, 6.0, 9.0], [2.0, 5.0, 8.0], [1.0, 4.0, 7.0]]
# get a two dimensional array but stack columns
data = pe.to_array(sheet.columns())
print(data)
# [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]
# get a two dimensional array but stack columns
# in reverse order
data = pe.to_array(sheet.rcolumns())
print(data)
#[[7.0, 8.0, 9.0], [4.0, 5.0, 6.0], [1.0, 2.0, 3.0]]
# filter out odd rows and even columns
sheet.filter(pe.OddRowFilter())
sheet.filter(pe.EvenColumnFilter())
data = sheet.to_dict()
print(data)
# {u'Column 3': [8.0], u'Column 1': [2.0]}
# and you can write the filtered results
# into a file
sheet.save_as("example_series_filter.xls")
# for i in tweet:
# print i
# print "\n"
trainclf = SVC(kernel='rbf', gamma=0.5)
sc = 0
fulltext = []
fullutext = []
fulltag = []
book = pyexcel.get_book(file_name="English_Train-final.xlsx")
for sheet in book:
if sc == 3:
break
data = pyexcel.to_array(sheet.rows())
text = []
utext = []
tag = []
for tweet in data:
tx = tweet[0]
tx = clean(tx)
utext.append(tweet[0])
text.append(tx)
tag.append(tweet[1])
fullutext.append(tweet[0])
fulltext.append(tx)
fulltag.append(tweet[1])
# for i,r in df.iterrows():
# tx=r['text']
def main(base_dir):
# print all in json
#
# Column 1 Column 2 Column 3
# 1 4 7
# 2 5 8
# 3 6 9
sheet = pe.get_sheet(file_name=os.path.join(base_dir,
"example_series.ods"),
name_columns_by_row=0)
print(json.dumps(sheet.to_dict()))
# output:
# {"Column 2": [4.0, 5.0, 6.0], "Column 3": [7.0, 8.0, 9.0],
# "Column 1": [1.0, 2.0, 3.0]}
# get the column headers
print(sheet.colnames)
# [u'Column 1', u'Column 2', u'Column 3']
# get the content in one dimensional array
data = pe.to_array(sheet.enumerate())
print(data)
# [1.0, 4.0, 7.0, 2.0, 5.0, 8.0, 3.0, 6.0, 9.0]
# get the content in one dimensional array
# in reverse order
data = pe.to_array(sheet.reverse())
print(data)
# get the content in one dimensional array
# but iterate it vertically
data = pe.to_array(sheet.vertical())
print(data)
# [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
# get the content in one dimensional array
# but iterate it vertically in revserse
# order
data = pe.to_array(sheet.rvertical())
print(data)
# [9.0, 8.0, 7.0, 6.0, 5.0, 4.0, 3.0, 2.0, 1.0]
# get a two dimensional array
data = pe.to_array(sheet.rows())
print(data)
# [[1.0, 4.0, 7.0], [2.0, 5.0, 8.0], [3.0, 6.0, 9.0]]
# get a two dimensional array in reverse
# order
data = pe.to_array(sheet.rrows())
print(data)
# [[3.0, 6.0, 9.0], [2.0, 5.0, 8.0], [1.0, 4.0, 7.0]]
# get a two dimensional array but stack columns
data = pe.to_array(sheet.columns())
print(data)
# [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]
# get a two dimensional array but stack columns
# in reverse order
data = pe.to_array(sheet.rcolumns())
print(data)
# [[7.0, 8.0, 9.0], [4.0, 5.0, 6.0], [1.0, 2.0, 3.0]]
# filter out odd rows and even columns
sheet.filter(pe.OddRowFilter())
sheet.filter(pe.EvenColumnFilter())
data = sheet.to_dict()
print(data)
# {u'Column 3': [8.0], u'Column 1': [2.0]}
# and you can write the filtered results
# into a file
sheet.save_as("example_series_filter.xls")
return p
def lastex(sent):
# print("out ex")
return sent[len(sent)-1]=='!'
def lastq(sent):
# print("out q")
return sent[len(sent)-1]=='?'
book = pyexcel.get_book(file_name="English_Train-final.xlsx")
for sheet in book:
text=[]
tag=[]
data=pyexcel.to_array(sheet.rows())
for tweet in data:
tx=tweet[0]
tx=clean(tx)
text.append(tx)
if(tweet[1]==2):
tag.append(tweet[2])
tag.append(tweet[1])
textlist=[]
c=0
for sent in text:
# textlist.append([has_modal(s),has_strong(s),has_personal(s),has_long(s), has_wh(s)])
textlist.append([has_long(sent), checknegation(sent), getnrcscore(sent),getemoscore(sent),
counthashtags(sent), countupper(sent), lastex(sent), lastq(sent),gets140_bi(sent),gets140_uni(sent),gets140_an_bi(sent), gets140_an_uni(sent)])
#
# Column 1 Column 2 Column 3
# 1 4 7
# 2 5 8
# 3 6 9
sheet = pe.load("example_series.ods", name_colmns_by_row=0)
print json.dumps(sheet.to_dict())
# output:
# {"Column 2": [4.0, 5.0, 6.0], "Column 3": [7.0, 8.0, 9.0], "Column 1": [1.0, 2.0, 3.0]}
# get the column headers
print sheet.colnames()
# [u'Column 1', u'Column 2', u'Column 3']
# get the content in one dimensional array
data = pe.to_array(sheet.enumerate())
print data
# [1.0, 4.0, 7.0, 2.0, 5.0, 8.0, 3.0, 6.0, 9.0]
# get the content in one dimensional array
# in reverse order
data = pe.to_array(sheet.reverse())
print data
# get the content in one dimensional array
# but iterate it vertically
data = pe.to_array(sheet.vertical())
print data
# [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0]
# get the content in one dimensional array