def _check_extension(self, ext):
path = "__tmp_to_excel_from_excel__." + ext
with ensure_clean(path) as path:
self.frame["A"][:5] = nan
self.frame.to_excel(path, "test1")
self.frame.to_excel(path, "test1", cols=["A", "B"])
self.frame.to_excel(path, "test1", header=False)
self.frame.to_excel(path, "test1", index=False)
# test roundtrip
self.frame.to_excel(path, "test1")
recons = read_excel(path, "test1", index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, "test1", index=False)
recons = read_excel(path, "test1", index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, "test1", na_rep="NA")
recons = read_excel(path, "test1", index_col=0, na_values=["NA"])
tm.assert_frame_equal(self.frame, recons)
# GH 3611
self.frame.to_excel(path, "test1", na_rep="88")
recons = read_excel(path, "test1", index_col=0, na_values=["88"])
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, "test1", na_rep="88")
recons = read_excel(path, "test1", index_col=0, na_values=[88, 88.0])
tm.assert_frame_equal(self.frame, recons)
def test_roundtrip(self):
_skip_if_no_xlrd()
ext = self.ext
path = '__tmp_to_excel_from_excel__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# test roundtrip
self.frame.to_excel(path, 'test1')
recons = read_excel(path, 'test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', index=False)
recons = read_excel(path, 'test1', index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='NA')
recons = read_excel(path, 'test1', index_col=0, na_values=['NA'])
tm.assert_frame_equal(self.frame, recons)
# GH 3611
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0, na_values=['88'])
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0, na_values=[88,88.0])
tm.assert_frame_equal(self.frame, recons)
def test_roundtrip(self):
_skip_if_no_xlrd()
with ensure_clean(self.ext) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# test roundtrip
self.frame.to_excel(path, 'test1')
recons = read_excel(path, 'test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', index=False)
recons = read_excel(path, 'test1', index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='NA')
recons = read_excel(path, 'test1', index_col=0, na_values=['NA'])
tm.assert_frame_equal(self.frame, recons)
# GH 3611
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0, na_values=['88'])
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0,
na_values=[88, 88.0])
tm.assert_frame_equal(self.frame, recons)
def _check_extension(self, ext):
path = '__tmp_to_excel_from_excel__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# test roundtrip
self.frame.to_excel(path, 'test1')
recons = read_excel(path, 'test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', index=False)
recons = read_excel(path, 'test1', index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='NA')
recons = read_excel(path, 'test1', index_col=0, na_values=['NA'])
tm.assert_frame_equal(self.frame, recons)
# GH 3611
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0, na_values=['88'])
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='88')
recons = read_excel(path, 'test1', index_col=0, na_values=[88,88.0])
tm.assert_frame_equal(self.frame, recons)
def test_read_from_http_url(self):
_skip_if_no_xlrd()
url = ('https://raw.github.com/pydata/pandas/master/'
'pandas/io/tests/data/test.xlsx')
url_table = read_excel(url)
dirpath = tm.get_data_path()
localtable = os.path.join(dirpath, 'test.xlsx')
local_table = read_excel(localtable)
tm.assert_frame_equal(url_table, local_table)
def test_read_from_http_url(self):
_skip_if_no_xlrd()
url = ('https://raw.github.com/pydata/pandas/master/'
'pandas/io/tests/data/test.xlsx')
url_table = read_excel(url)
dirpath = tm.get_data_path()
localtable = os.path.join(dirpath, 'test.xlsx')
local_table = read_excel(localtable)
tm.assert_frame_equal(url_table, local_table)
def main():
global default_user
global default_pass
global default_secret
global arguments
#read arn parse arguments from command line
arguments = getargs()
# device_queue.maxsize(arguments.qs)
print('Setting max Queue size to: ', arguments.qs)
device_queue.maxsize = int(arguments.qs)
worksheets = {}
default_user = getusername()
default_pass = getpassword(default_user)
default_secret = getpassword('enable/secret')
# Initializes the threads.
CreateThreads(arguments.ts)
with excel.ExcelFile(arguments.inputfile) as wb:
for sname in wb.sheet_names:
print('**** Sheet Name: '+ str(sname))
readsheet = excel.read_excel(wb,sheet_name=sname,converters={'Username':str,'Password':str,'Secret':str,'data_type':str,'Show_Commands':str,'Config_Commands':str})
df = DataFrame(data=readsheet, copy=True)
worksheets[sname] = df.to_dict(orient='records')
for rw in worksheets[sname]:
device_queue.put(rw)
device_queue.join()
print(threading.enumerate())
print('Playbook completed successfully!!')
def readTARAxls(datafile, headerline):
df = read_excel(datafile, header=headerline)
df.columns = _fix_header(df.iloc[2])
df = df.drop(range(4))
df = df.rename(columns = {'Sample ID':'TARA_SampleID', 'Sample ID.2':'SampleID'})\
.drop(['Sample ID.1', 'PARAMETER'], axis=1).set_index('SampleID')
return df.loc[df.index != 'none']
def main(workshop, mailchimpdir):
if not os.path.isdir(mailchimpdir):
print(mailchimpdir, 'must be a directory.')
return
wdict = {}
wdf = ex.read_excel(workshop, 'Sheet1', parse_cols=(0, 1, 2))
wdf.rename(columns={
'Surname': 'surname',
'First name': 'first_name',
'Email address': 'email_address'
},
inplace=True)
wdf.dropna(subset=['email_address'], inplace=True)
wdf.fillna('', inplace=True)
for c in wdf.columns:
wdf[c] = wdf[c].str.strip()
for row in wdf.itertuples():
wdict[row.email_address] = make_entry(row)
# print(wdict)
for filename in os.listdir(mailchimpdir):
if not filename.endswith('.csv'):
continue
prune(wdict, mailchimpdir, filename)
print('Workshop emails:', len(wdict))
outdir = os.path.dirname(workshop)
outdir = os.path.join(outdir, 'results')
os.makedirs(outdir, exist_ok=True)
outfilename = _starttime.strftime("workshop_emails_%Y%m%d-%H%M%S.csv")
outpath = os.path.join(outdir, outfilename)
with open(outpath, 'w', newline='') as outfile:
outwriter = csv.writer(outfile)
outwriter.writerow('email surname firstname'.split())
for k in sorted(wdict):
outwriter.writerow(wdict[k])
def test_read_from_file_url(self):
_skip_if_no_xlrd()
# FILE
if sys.version_info[:2] < (2, 6):
raise nose.SkipTest("file:// not supported with Python < 2.6")
dirpath = tm.get_data_path()
localtable = os.path.join(dirpath, 'test.xlsx')
local_table = read_excel(localtable)
try:
url_table = read_excel('file://localhost/' + localtable)
except URLError:
# fails on some systems
raise nose.SkipTest("failing on %s" %
' '.join(platform.uname()).strip())
tm.assert_frame_equal(url_table, local_table)
def test_read_from_file_url(self):
_skip_if_no_xlrd()
# FILE
if sys.version_info[:2] < (2, 6):
raise nose.SkipTest("file:// not supported with Python < 2.6")
dirpath = tm.get_data_path()
localtable = os.path.join(dirpath, 'test.xlsx')
local_table = read_excel(localtable)
try:
url_table = read_excel('file://localhost/' + localtable)
except URLError:
# fails on some systems
raise nose.SkipTest("failing on %s" %
' '.join(platform.uname()).strip())
tm.assert_frame_equal(url_table, local_table)
def test_reader_seconds(self):
# Test reading times with and without milliseconds. GH5945.
_skip_if_no_xlrd()
import xlrd
if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
# Xlrd >= 0.9.3 can handle Excel milliseconds.
expected = DataFrame.from_items([("Time", [
time(1, 2, 3),
time(2, 45, 56, 100000),
time(4, 29, 49, 200000),
time(6, 13, 42, 300000),
time(7, 57, 35, 400000),
time(9, 41, 28, 500000),
time(11, 25, 21, 600000),
time(13, 9, 14, 700000),
time(14, 53, 7, 800000),
time(16, 37, 0, 900000),
time(18, 20, 54)
])])
else:
# Xlrd < 0.9.3 rounds Excel milliseconds.
expected = DataFrame.from_items([("Time", [
time(1, 2, 3),
time(2, 45, 56),
time(4, 29, 49),
time(6, 13, 42),
time(7, 57, 35),
time(9, 41, 29),
time(11, 25, 22),
time(13, 9, 15),
time(14, 53, 8),
time(16, 37, 1),
time(18, 20, 54)
])])
epoch_1900 = os.path.join(self.dirpath, 'times_1900.xls')
epoch_1904 = os.path.join(self.dirpath, 'times_1904.xls')
actual = read_excel(epoch_1900, 'Sheet1')
tm.assert_frame_equal(actual, expected)
actual = read_excel(epoch_1904, 'Sheet1')
tm.assert_frame_equal(actual, expected)
def test_reader_seconds(self):
# Test reading times with and without milliseconds. GH5945.
_skip_if_no_xlrd()
import xlrd
if LooseVersion(xlrd.__VERSION__) >= LooseVersion("0.9.3"):
# Xlrd >= 0.9.3 can handle Excel milliseconds.
expected = DataFrame.from_items([("Time",
[time(1, 2, 3),
time(2, 45, 56, 100000),
time(4, 29, 49, 200000),
time(6, 13, 42, 300000),
time(7, 57, 35, 400000),
time(9, 41, 28, 500000),
time(11, 25, 21, 600000),
time(13, 9, 14, 700000),
time(14, 53, 7, 800000),
time(16, 37, 0, 900000),
time(18, 20, 54)])])
else:
# Xlrd < 0.9.3 rounds Excel milliseconds.
expected = DataFrame.from_items([("Time",
[time(1, 2, 3),
time(2, 45, 56),
time(4, 29, 49),
time(6, 13, 42),
time(7, 57, 35),
time(9, 41, 29),
time(11, 25, 22),
time(13, 9, 15),
time(14, 53, 8),
time(16, 37, 1),
time(18, 20, 54)])])
epoch_1900 = os.path.join(self.dirpath, 'times_1900.xls')
epoch_1904 = os.path.join(self.dirpath, 'times_1904.xls')
actual = read_excel(epoch_1900, 'Sheet1')
tm.assert_frame_equal(actual, expected)
actual = read_excel(epoch_1904, 'Sheet1')
tm.assert_frame_equal(actual, expected)
def main():
cartoons = ex.read_excel(WORKBOOK, 'Sheet1')
cartoons.dropna(inplace=True)
# cartoons['ISODate'] = pd.to_datetime(cartoons.ISODate)
cartoons['Year'] = cartoons.ISODate.dt.year.astype('int')
c = cartoons.groupby('Year').count()
p = c.ISODate.plot(kind='bar', legend=False)
fig = p.get_figure()
fig.savefig(BARPLOT)
Image.open(BARPLOT).save(BARPLOT[:-4] + '.jpg', 'JPEG')
print('Exit plot.')
def init_piaofang_history_data(self):
try:
temp = read_excel(self.piaofang_history_fname)
except IOError as e:
print(e)
return None
ds = [x.date() for x in temp['发布时间']]
temp.index = diff_date(self.pub_date, ds)
self.piaofang_h = temp.drop(['内部编号','发布时间','收集时间',
'更新时间'], axis=1).groupby(level=0).max()
def init_gewara_data(self):
try:
temp = read_excel(self.gewara_fname)
except IOError as e:
print(e)
return None
ds = [x.date() for x in temp['收集时间']]
temp.index = diff_date(self.pub_date, ds)
self.gewara_f = temp.drop(['内部编号', '格瓦拉编号',
'收集时间', '更新时间'], axis=1).groupby(level=0).max()
def init_douban_comment(self):
try:
temp = read_excel(self.douban_fname)
except IOError as e:
print(e)
return None
ds = np.array([x.date() for x in temp['收集时间']])
temp.index = diff_date(self.pub_date, ds)
self.douban_f = temp.drop(['内部编号','豆瓣编号',
'收集时间','更新时间'], axis = 1)
def init_baidu_index(self):
try:
temp = read_excel(self.baidu_fname)
except IOError as msg:
print(e)
return None
ds = [x.date() for x in temp['收集时间']]
temp.index = diff_date(self.pub_date, ds)
self.baidu_f = temp.drop(['内部编号','搜索类型','搜索排名',
'搜索趋势','收集时间','更新时间'], axis=1).groupby(level=0).max()
def test_to_excel_output_encoding(self):
_skip_if_no_xlrd()
ext = self.ext
filename = '__tmp_to_excel_float_format__.' + ext
df = DataFrame([[u('\u0192'), u('\u0193'), u('\u0194')],
[u('\u0195'), u('\u0196'), u('\u0197')]],
index=[u('A\u0192'), 'B'], columns=[u('X\u0193'), 'Y', 'Z'])
with ensure_clean(filename) as filename:
df.to_excel(filename, sheet_name='TestSheet', encoding='utf8')
result = read_excel(filename, 'TestSheet', encoding='utf8')
tm.assert_frame_equal(result, df)
def test_swapped_columns(self):
# Test for issue #5427.
_skip_if_no_xlrd()
with ensure_clean(self.ext) as path:
write_frame = DataFrame({'A': [1, 1, 1], 'B': [2, 2, 2]})
write_frame.to_excel(path, 'test1', cols=['B', 'A'])
read_frame = read_excel(path, 'test1', header=0)
tm.assert_series_equal(write_frame['A'], read_frame['A'])
tm.assert_series_equal(write_frame['B'], read_frame['B'])
def getbasemetadata():
df = read_excel(Biodata.TARA.SeqContextXL, header=16)
df = df.drop(range(4)).rename(columns={'Analysis ID.1':'experiment_accession'})\
.set_index('experiment_accession')
sample_sheet = read_csv(RawFastq.TARA.SampleSheet,
sep='\t').set_index('experiment_accession')
df = sample_sheet.join(df)
df['RunID'] = df['run_accession']
df['SampleID'] = df['secondary_sample_accession']
df = df[df['submitted_ftp'].apply(lambda x: '.fastq.gz' in x)]
df['Fastq_1'] = df['submitted_ftp'].apply(
lambda x: join(RawFastq.TARA.FastqDir, basename(x.split(';')[0])))
df['Fastq_2'] = df['submitted_ftp'].apply(
lambda x: join(RawFastq.TARA.FastqDir, basename(x.split(';')[0])))
df['ICRABAM_1'] = df['submitted_ftp'].apply(lambda x: join(
Mapping.OM_RGC.MapDir,
basename(x.split(';')[0].replace('.fastq.gz', '.icra.bam'))))
df['ICRABAM_2'] = df['submitted_ftp'].apply(lambda x: join(
Mapping.OM_RGC.MapDir,
basename(x.split(';')[1].replace('.fastq.gz', '.icra.bam'))))
df = df.rename(
columns={
'Sample ID': 'TARA_SampleID',
'Analysis label': 'Analysis_label',
'Environmental feature': 'Environmental_feature',
'Size fraction, lower threshold': 'Size_min',
'Size fraction, upper threshold': 'Size_max',
'Depth, top/min': 'Depth_min',
'Depth, bottom/max': 'Depth_max',
'Event label': 'Event_label',
'Station label': 'Station_label'
})
df['Collection_datetime'] = df['Event_label'].dropna()\
.apply(lambda x: datetime.strptime(x.split('_')[1],
'%Y%m%dT%H%MZ'))
stations = read_csv(Biodata.TARA.Stations, sep='\t')
df['Latitude'] = df['Station_label'].dropna()\
.apply(lambda x: stations[stations['Station'] == x]['Latitude'].values[0])
df['Longitude'] = df['Station_label'].dropna()\
.apply(lambda x: stations[stations['Station'] == x]['Longitude'].values[0])
df['Depth'] = df[['Depth_min', 'Depth_max']].astype(float).mean(1)
df['Cruise_series'] = 'TARA'
df = df[[
'SampleID', 'RunID', 'Cruise_series', 'Collection_datetime',
'Latitude', 'Longitude', 'Depth', 'TARA_SampleID', 'Analysis_label',
'Event_label', 'Station_label', 'Environmental_feature', 'Size_min',
'Size_max', 'Depth_min', 'Depth_max', 'Fastq_1', 'Fastq_2',
'ICRABAM_1', 'ICRABAM_2'
]]
df = df.reset_index().set_index(['SampleID', 'RunID'])
df.to_pickle(Biodata.TARA.metadataDF)
return df['experiment_accession'].values
def test_int_types(self):
_skip_if_no_xlrd()
for np_type in (np.int8, np.int16, np.int32, np.int64):
with ensure_clean(self.ext) as path:
# Test np.int values read come back as int (rather than float
# which is Excel's format).
frame = DataFrame(np.random.randint(-10, 10, size=(10, 2)),
dtype=np_type)
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
int_frame = frame.astype(int)
tm.assert_frame_equal(int_frame, recons)
recons2 = read_excel(path, 'test1')
tm.assert_frame_equal(int_frame, recons2)
# test with convert_float=False comes back as float
float_frame = frame.astype(float)
recons = read_excel(path, 'test1', convert_float=False)
tm.assert_frame_equal(recons, float_frame)
def test_int_types(self):
_skip_if_no_xlrd()
for np_type in (np.int8, np.int16, np.int32, np.int64):
with ensure_clean(self.ext) as path:
# Test np.int values read come back as int (rather than float
# which is Excel's format).
frame = DataFrame(np.random.randint(-10, 10, size=(10, 2)),
dtype=np_type)
frame.to_excel(path, 'test1')
reader = ExcelFile(path)
recons = reader.parse('test1')
int_frame = frame.astype(np.int64)
tm.assert_frame_equal(int_frame, recons)
recons2 = read_excel(path, 'test1')
tm.assert_frame_equal(int_frame, recons2)
# test with convert_float=False comes back as float
float_frame = frame.astype(float)
recons = read_excel(path, 'test1', convert_float=False)
tm.assert_frame_equal(recons, float_frame)
def test_swapped_columns(self):
# Test for issue #5427.
_skip_if_no_xlrd()
with ensure_clean(self.ext) as path:
write_frame = DataFrame({'A': [1, 1, 1],
'B': [2, 2, 2]})
write_frame.to_excel(path, 'test1', columns=['B', 'A'])
read_frame = read_excel(path, 'test1', header=0)
tm.assert_series_equal(write_frame['A'], read_frame['A'])
tm.assert_series_equal(write_frame['B'], read_frame['B'])
def test_to_excel_output_encoding(self):
_skip_if_no_xlrd()
ext = self.ext
filename = '__tmp_to_excel_float_format__.' + ext
df = DataFrame(
[[u('\u0192'), u('\u0193'), u('\u0194')],
[u('\u0195'), u('\u0196'), u('\u0197')]],
index=[u('A\u0192'), 'B'],
columns=[u('X\u0193'), 'Y', 'Z'])
with ensure_clean(filename) as filename:
df.to_excel(filename, sheet_name='TestSheet', encoding='utf8')
result = read_excel(filename, 'TestSheet', encoding='utf8')
tm.assert_frame_equal(result, df)
def create_df(self):
if self.file_path.endswith('.csv'):
df = pd.read_csv(self.file_path)
else:
wb = xlrd.open_workbook(self.file_path)
sheet = wb.sheets()[0]
df = read_excel(self.file_path,sheet.name)
df_no_nan = df.where((pd.notnull(df)), None)
return df_no_nan
def test_duplicated_columns(self):
# Test for issue #5235.
_skip_if_no_xlrd()
with ensure_clean(self.ext) as path:
write_frame = DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]])
colnames = ['A', 'B', 'B']
write_frame.columns = colnames
write_frame.to_excel(path, 'test1')
read_frame = read_excel(path, 'test1')
read_frame.columns = colnames
tm.assert_frame_equal(write_frame, read_frame)
def test_duplicated_columns(self):
# Test for issue #5235.
_skip_if_no_xlrd()
with ensure_clean(self.ext) as path:
write_frame = DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]])
colnames = ['A', 'B', 'B']
write_frame.columns = colnames
write_frame.to_excel(path, 'test1')
read_frame = read_excel(path, 'test1')
read_frame.columns = colnames
tm.assert_frame_equal(write_frame, read_frame)
def _check_extension(self, ext):
path = '__tmp_to_excel_from_excel__.' + ext
with ensure_clean(path) as path:
self.frame['A'][:5] = nan
self.frame.to_excel(path, 'test1')
self.frame.to_excel(path, 'test1', cols=['A', 'B'])
self.frame.to_excel(path, 'test1', header=False)
self.frame.to_excel(path, 'test1', index=False)
# test roundtrip
self.frame.to_excel(path, 'test1')
recons = read_excel(path, 'test1', index_col=0)
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', index=False)
recons = read_excel(path, 'test1', index_col=None)
recons.index = self.frame.index
tm.assert_frame_equal(self.frame, recons)
self.frame.to_excel(path, 'test1', na_rep='NA')
recons = read_excel(path, 'test1', index_col=0, na_values=['NA'])
tm.assert_frame_equal(self.frame, recons)
def test_reader_special_dtypes(self):
_skip_if_no_xlrd()
expected = DataFrame.from_items([
("IntCol", [1, 2, -3, 4, 0]),
("FloatCol", [1.25, 2.25, 1.83, 1.92, 0.0000000005]),
("BoolCol", [True, False, True, True, False]),
("StrCol", [1, 2, 3, 4, 5]),
# GH5394 - this is why convert_float isn't vectorized
("Str2Col", ["a", 3, "c", "d", "e"]),
("DateCol", [
datetime(2013, 10, 30),
datetime(2013, 10, 31),
datetime(1905, 1, 1),
datetime(2013, 12, 14),
datetime(2015, 3, 14)
])
])
xlsx_path = os.path.join(self.dirpath, 'test_types.xlsx')
xls_path = os.path.join(self.dirpath, 'test_types.xls')
# should read in correctly and infer types
for path in (xls_path, xlsx_path):
actual = read_excel(path, 'Sheet1')
tm.assert_frame_equal(actual, expected)
# if not coercing number, then int comes in as float
float_expected = expected.copy()
float_expected["IntCol"] = float_expected["IntCol"].astype(float)
float_expected.loc[1, "Str2Col"] = 3.0
for path in (xls_path, xlsx_path):
actual = read_excel(path, 'Sheet1', convert_float=False)
tm.assert_frame_equal(actual, float_expected)
# check setting Index (assuming xls and xlsx are the same here)
for icol, name in enumerate(expected.columns):
actual = read_excel(xlsx_path, 'Sheet1', index_col=icol)
actual2 = read_excel(xlsx_path, 'Sheet1', index_col=name)
exp = expected.set_index(name)
tm.assert_frame_equal(actual, exp)
tm.assert_frame_equal(actual2, exp)
# convert_float and converters should be different but both accepted
expected["StrCol"] = expected["StrCol"].apply(str)
actual = read_excel(xlsx_path, 'Sheet1', converters={"StrCol": str})
tm.assert_frame_equal(actual, expected)
no_convert_float = float_expected.copy()
no_convert_float["StrCol"] = no_convert_float["StrCol"].apply(str)
actual = read_excel(xlsx_path,
'Sheet1',
converters={"StrCol": str},
convert_float=False)
tm.assert_frame_equal(actual, no_convert_float)
def test_duplicated_columns(self):
# Test for issue #5235.
_skip_if_no_xlrd()
ext = self.ext
path = '__tmp_to_excel_duplicated_columns__.' + ext
with ensure_clean(path) as path:
write_frame = DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]])
colnames = ['A', 'B', 'B']
write_frame.columns = colnames
write_frame.to_excel(path, 'test1')
read_frame = read_excel(path, 'test1').astype(np.int64)
read_frame.columns = colnames
tm.assert_frame_equal(write_frame, read_frame)
def test_duplicated_columns(self):
# Test for issue #5235.
_skip_if_no_xlrd()
ext = self.ext
path = '__tmp_to_excel_duplicated_columns__.' + ext
with ensure_clean(path) as path:
write_frame = DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]])
colnames = ['A', 'B', 'B']
write_frame.columns = colnames
write_frame.to_excel(path, 'test1')
read_frame = read_excel(path, 'test1').astype(np.int64)
read_frame.columns = colnames
tm.assert_frame_equal(write_frame, read_frame)
def test_read_xlrd_Book(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
import xlrd
df = self.frame
with ensure_clean('.xls') as pth:
df.to_excel(pth, "SheetA")
book = xlrd.open_workbook(pth)
with ExcelFile(book, engine="xlrd") as xl:
result = xl.parse("SheetA")
tm.assert_frame_equal(df, result)
result = read_excel(book, sheetname="SheetA", engine="xlrd")
tm.assert_frame_equal(df, result)
def test_read_xlrd_Book(self):
_skip_if_no_xlrd()
_skip_if_no_xlwt()
import xlrd
df = self.frame
with ensure_clean('.xls') as pth:
df.to_excel(pth, "SheetA")
book = xlrd.open_workbook(pth)
with ExcelFile(book, engine="xlrd") as xl:
result = xl.parse("SheetA")
tm.assert_frame_equal(df, result)
result = read_excel(book, sheetname="SheetA", engine="xlrd")
tm.assert_frame_equal(df, result)
def test_reader_special_dtypes(self):
_skip_if_no_xlrd()
expected = DataFrame.from_items([
("IntCol", [1, 2, -3, 4, 0]),
("FloatCol", [1.25, 2.25, 1.83, 1.92, 0.0000000005]),
("BoolCol", [True, False, True, True, False]),
("StrCol", [1, 2, 3, 4, 5]),
# GH5394 - this is why convert_float isn't vectorized
("Str2Col", ["a", 3, "c", "d", "e"]),
("DateCol", [datetime(2013, 10, 30), datetime(2013, 10, 31),
datetime(1905, 1, 1), datetime(2013, 12, 14),
datetime(2015, 3, 14)])
])
xlsx_path = os.path.join(self.dirpath, 'test_types.xlsx')
xls_path = os.path.join(self.dirpath, 'test_types.xls')
# should read in correctly and infer types
for path in (xls_path, xlsx_path):
actual = read_excel(path, 'Sheet1')
tm.assert_frame_equal(actual, expected)
# if not coercing number, then int comes in as float
float_expected = expected.copy()
float_expected["IntCol"] = float_expected["IntCol"].astype(float)
float_expected.loc[1, "Str2Col"] = 3.0
for path in (xls_path, xlsx_path):
actual = read_excel(path, 'Sheet1', convert_float=False)
tm.assert_frame_equal(actual, float_expected)
# check setting Index (assuming xls and xlsx are the same here)
for icol, name in enumerate(expected.columns):
actual = read_excel(xlsx_path, 'Sheet1', index_col=icol)
actual2 = read_excel(xlsx_path, 'Sheet1', index_col=name)
exp = expected.set_index(name)
tm.assert_frame_equal(actual, exp)
tm.assert_frame_equal(actual2, exp)
# convert_float and converters should be different but both accepted
expected["StrCol"] = expected["StrCol"].apply(str)
actual = read_excel(xlsx_path, 'Sheet1', converters={"StrCol": str})
tm.assert_frame_equal(actual, expected)
no_convert_float = float_expected.copy()
no_convert_float["StrCol"] = no_convert_float["StrCol"].apply(str)
actual = read_excel(xlsx_path, 'Sheet1', converters={"StrCol": str},
convert_float=False)
tm.assert_frame_equal(actual, no_convert_float)
import pandas.io.excel as x
df = x.read_excel("/home/burak/Downloads/CNTSDATA.xls")
df.to_csv("/tmp/CNTSDATA.csv", encoding="utf-8")
if not os.path.exists(dataset_fname):
download(dataset_url, server_fname=dataset_fname)
"""
The dataset is stored as an Excel spreadsheet (XLS).
We can read it without unzipping using the zipfile library.
"""
archive = zipfile.ZipFile(dataset_fname, 'r')
# Only one file in the zipfile we are reading from
# archive.open returns a file-like object - perfect for sending to pandas
file_handle = archive.open(archive.infolist()[0])
"""
To read the actual XLS file, we can use pandas.
"""
dataframe = read_excel(file_handle)
data = dataframe.values
"""
Only use the first 100 users for this example.
"""
user_indices = data[:100, 0]
ratings = data[:100, 1:]
# Necessary because this is a view of the underlying data, want separate copy
true_ratings = np.copy(data[:100, 1:])
"""
In this dataset, any rating of 99. means that a joke was unrated. Since these
are floating point values, it is best to create the sparse array by hand.
We can get these indices with np.where.
"""
def ReadWorkBookIntoQueue(inputSubPlan, portMatrix):
next_service = False
worksheets = {}
ManagementIP = ''
ManagementMask = ''
ManagementVLAN = ''
dataSubnet = ''
Subnetmask = 0
current_floor = 0
current_IDF_ID = ''
current_service = ''
mgmtIPoctect = 0
mgmtIPTracker = 0
portmatrixwb = excel.ExcelFile(portMatrix)
if arguments.configtype.upper() == 'AL':
configt = 'Data'
elif arguments.configtype.upper() == 'WL':
configt = 'Wireless'
else:
configt = 'Security Cameras'
with excel.ExcelFile(inputSubPlan) as wb:
for sname in wb.sheet_names:
print('**** Sheet Name: '+ str(sname))
#readsheet = excel.read_excel(wb,sheet_name=sname,converters={'Username':str,'Password':str,'Secret':str,'data_type':str,'Show_Commands':str,'Config_Commands':str})
readsheet = excel.read_excel(wb,sheet_name=sname)
df = DataFrame(data=readsheet, copy=True)
worksheets[sname] = df.to_dict(orient='records')
print('Finding management subnet and VLAN: \n')
for rw in worksheets[sname]:
if rw.get('Service') == 'Wired Switch Management' and configt == 'Data':
ManagementIP, ManagementMask = str(rw.get('Assigned Subnets')).split('/')
ManagementVLAN = rw.get('VLAN')
break
elif rw.get('Service') == 'Wireless Switch Management' and configt == 'Wireless':
ManagementIP, ManagementMask = str(rw.get('Assigned Subnets')).split('/')
ManagementVLAN = rw.get('VLAN')
break
else:
if rw.get('Service') == 'Security Switch Management' and configt == 'Security Cameras':
ManagementIP, ManagementMask = str(rw.get('Assigned Subnets')).split('/')
ManagementVLAN = rw.get('VLAN')
break
for rw in worksheets[sname]:
if next_service and rw.get('Service') == rw.get('Service'):
break
if rw.get('Service') == configt:
current_service = str(rw.get('Service')).strip()
print('found service: ', rw.get('Service'))
if (current_service == configt):
print('processing next...')
switch_dict = {'jinjatemplate': '', 'hostname': '', 'IDFID': '', 'managementMask': '', 'ManagementIP': '', \
'datavlanname': '', 'datavlans': [], 'datasubnet': '', 'datamask': '', 'voicevlanname': '', \
'voicevlans': [], 'voicesubnet': '', 'voicemask': '', 'managementVLAN': '', 'managmentsubnet': '', \
'po': {'ponum': '', 'interfaces': {}}}
next_service = True
# find current floor and assign 10 to mgmtIPoctect for management last octect
if rw.get('Floor') == rw.get('Floor'):
current_floor = rw.get('Floor')
mgmtIPTracker = mgmtIPTracker + 1
mgmtIPoctect = (mgmtIPTracker * 10) + 1
# Gets IDFID base on Switch name
if rw.get('Switch') == rw.get('Switch'):
current_IDF_ID = str(rw.get('Switch').upper())
#current_IDF_ID = current_IDF_ID.replace('-','_')
current_IDF_ID = current_IDF_ID.replace('_AL1','')
current_IDF_ID = current_IDF_ID.replace('_AL2','')
current_IDF_ID = current_IDF_ID.replace('_AL3','')
current_IDF_ID = current_IDF_ID.replace('_WL1','')
current_IDF_ID = current_IDF_ID.replace('_SE1','')
current_IDF_ID = GenVlanName("",current_IDF_ID)
if rw.get('Assigned Subnets') == rw.get('Assigned Subnets'):
dataSubnet, Subnetmask = str(rw.get('Assigned Subnets')).split('/')
switch_dict['jinjatemplate'] = templatefile
switch_dict['hostname'] = str(rw.get('Switch')).upper()
switch_dict['IDFID'] = current_IDF_ID
switch_dict['datasubnet'] = dataSubnet.strip()
switch_dict['datamask'] = cidr_to_netmask(Subnetmask)
if configt == 'Data' or configt == 'Wireless':
switch_dict['datavlanname'] = GenVlanName(configt.upper() + '_',switch_dict['hostname'])
else:
temp_service, garbage = configt.split(" ")
switch_dict['datavlanname'] = GenVlanName(temp_service.upper() + '_',switch_dict['hostname'])
switch_dict['managmentsubnet'], garbage = str(ManagementIP).strip().split('.0',3)
switch_dict['managementMask'] = cidr_to_netmask(ManagementMask)
switch_dict['managementVLAN'] = str(ManagementVLAN).strip()
if current_service == 'Data':
portmatrixsh = portmatrixwb.parse(sheet_name='6807 Wired VSS')
print('Processing AL Port Matrix ...')
elif current_service == 'Security Cameras':
portmatrixsh = portmatrixwb.parse(sheet_name='6840 SEC VSS')
print('Processing SE Port Matrix ...')
else:
portmatrixsh = portmatrixwb.parse(sheet_name='6807 WL VSS')
print('Processing WL Port Matrix ...')
for pmxrow in portmatrixsh.to_records():
# apply this logic to AL tab in port matrix
if str(switch_dict['hostname']).upper().strip() == str(pmxrow[7]).upper().strip():
switch_dict['po']['ponum'] = pmxrow[5][2:].strip()
switch_dict['po']['interfaces'][pmxrow[8]] = pmxrow[1]
switch_dict['po']['interfaces'][pmxrow[19]] = pmxrow[13]
# apply this logic to fields on WL and SEC in port matrix
if str(switch_dict['hostname']).upper().strip() == str(pmxrow[6]).upper().strip():
switch_dict['po']['ponum'] = pmxrow[4][2:].strip()
switch_dict['po']['interfaces'][pmxrow[7]] = pmxrow[1]
switch_dict['po']['interfaces'][pmxrow[16]] = pmxrow[11]
vl = str(rw.get('VLAN')).split('\n')
for vlan in vl:
vlantoadd = str(vlan)
switch_dict['datavlans'].append(str(int(float(vlantoadd))))
if configt == 'Data':
switch_dict['ManagementIP'] = switch_dict['managmentsubnet'] + '.' + \
switch_dict['datavlans'][0][len(switch_dict['datavlans'])-3:]
else:
switch_dict['ManagementIP'] = switch_dict['managmentsubnet'] + '.' + str(mgmtIPoctect)
mgmtIPoctect = mgmtIPoctect + 1
# find voice vlan and add to dictionary
for vc in worksheets[sname]:
if vc.get('Service') == vc.get('Service'):
current_service_vc = vc.get('Service')
if current_service_vc == 'Voice' and str(vc.get('Switch')).upper() == str(switch_dict['hostname']).upper():
voiceSubnet, Subnetmask = str(vc.get('Assigned Subnets')).split('/')
switch_dict['voicevlanname'] = GenVlanName(current_service_vc.upper() + '_',switch_dict['hostname'])
switch_dict['voicesubnet'] = voiceSubnet.strip()
switch_dict['voicemask'] = cidr_to_netmask(Subnetmask)
vl = str(vc.get('VLAN')).split('\n')
for vlan in vl:
vlantoadd = str(vlan)
switch_dict['voicevlans'].append(str(int(float(vlantoadd))))
break
print(switch_dict, '\n')
print('Generating Config ....> ')
GenerateConfig(switch_dict)
device_queue.put(switch_dict)
import pandas.io.excel as x
df = x.read_excel('/home/burak/Downloads/CNTSDATA.xls')
df.to_csv('/tmp/CNTSDATA.csv', encoding='utf-8')
"""
dataset_fname = dataset_url.split("/")[-1]
if not os.path.exists(dataset_fname):
download(dataset_url, server_fname=dataset_fname)
"""
The dataset is stored as an Excel spreadsheet (XLS).
We can read it without unzipping using the zipfile library.
"""
archive = zipfile.ZipFile(dataset_fname, 'r')
# Only one file in the zipfile we are reading from
# archive.open returns a file-like object - perfect for sending to pandas
file_handle = archive.open(archive.infolist()[0])
"""
To read the actual XLS file, we can use pandas.
"""
dataframe = read_excel(file_handle)
data = dataframe.values
"""
Only use the first 100 users for this example.
"""
user_indices = data[:100, 0]
ratings = data[:100, 1:]
# Necessary because this is a view of the underlying data, want separate copy
true_ratings = np.copy(data[:100, 1:])
"""
In this dataset, any rating of 99. means that a joke was unrated. Since these
are floating point values, it is best to create the sparse array by hand.
We can get these indices with np.where.
"""
rated = np.where(ratings <= 10.)
np.random.RandomState(1999)
def main():
#read arn parse arguments from command line
arguments = getargs()
worksheets = {}
playbookinfo = {
'creds': {
'device_type': "",
'ip': "",
'username': "",
'password': "",
'secret': ""
},
'ShowCommands': [],
'ConfigCommands': []
}
with excel.ExcelFile(arguments.inputfile) as wb:
playbookinfo['ShowCommands'] = ''
playbookinfo['ConfigCommands'] = ''
for sname in wb.sheet_names:
print('**** Sheet Name: ' + str(sname))
readsheet = excel.read_excel(wb,sheet_name=sname,converters={'Username':str,'Password':str,'Secret':str,\
'data_type':str,'Show_Commands':str,'Config_Commands':str})
df = DataFrame(data=readsheet, copy=True)
worksheets[sname] = df.to_dict(orient='records')
for rw in worksheets[sname]:
playbookinfo['creds']['device_type'] = rw.get('device_type')
playbookinfo['creds']['ip'] = rw.get('IP')
# if username field in playbook is blank, interactively enter username
if rw.get('Username') != rw.get('Username') or rw.get(
'Username').strip() == '':
playbookinfo['creds']['username'] = getusername()
else:
playbookinfo['creds']['username'] = rw.get('Username')
print('\nLogin into: ' + playbookinfo['creds']['ip'] + ' ...')
# if password field in playbook is blank, interactively enter password
if rw.get('Password') != rw.get('Password') or rw.get(
'Password').strip() == '':
playbookinfo['creds']['password'] = getpassword(
playbookinfo['creds']['username'])
else:
playbookinfo['creds']['password'] = rw.get('Password')
# if secret field in playbook is blank ask user if it wants to enter one
if rw.get('Secret') != rw.get('Secret') or rw.get(
'Secret') == '':
if input(
'do you want to enter enabled/secret password(Y/N): '
).upper() == 'Y':
playbookinfo['creds']['secret'] = getpassword(
'secret/enabled')
else:
playbookinfo['creds']['secret'] = rw.get('Secret')
playbookinfo['ShowCommands'] = str(
rw.get('Show_Commands')).split('\n')
playbookinfo['ConfigCommands'] = str(
rw.get('Config_Commands')).split('\n')
conn = connectToDevice(playbookinfo['creds'])
resultprompt = conn.find_prompt()
if resultprompt[len(resultprompt) - 1] != "#":
print(
"----> Changing from User mode to privilege mode <----\n"
+ resultprompt)
conn.enable()
resultprompt = conn.find_prompt()
print(resultprompt)
else:
print("----> Already in privilege mode <----\n" +
resultprompt)
qalog = openlogfile(resultprompt, playbookinfo['creds']['ip'])
if (rw.get('Show_Commands') == rw.get('Show_Commands')) and \
len(str(rw.get('Show_Commands')).strip()) > 0 and rw.get('Config_Commands') != rw.get('Config_Commands'):
print(\
'*****************************************************\n' + \
'*** Running show commands ***\n' + \
'*****************************************************\n')
logshowcommands(qalog, conn, playbookinfo['ShowCommands'])
if (rw.get('Config_Commands') == rw.get('Config_Commands')) and \
len(str(rw.get('Config_Commands')).strip()) > 0:
print(\
'*****************************************************\n' + \
'*** Entering config mode ***\n' + \
'*****************************************************\n')
print(\
'*****************************************************\n' + \
'*** Running show commands - before changes ***\n' + \
'*****************************************************\n')
qalog.write(\
'*****************************************************\n' + \
'*** Running show commands - before changes ***\n' + \
'*****************************************************\n')
if rw.get('Show_Commands') == rw.get('Show_Commands'):
logshowcommands(qalog, conn,
playbookinfo['ShowCommands'])
else:
logshowcommands(qalog, conn, SHOWCOMMANDS)
configresults = conn.send_config_set(
config_commands=playbookinfo['ConfigCommands'])
print(\
'*****************************************************\n' + \
'*** Configurations Changes ***\n' + \
'*****************************************************\n')
print(configresults)
qalog.write(get_logheader('Configuration changes'))
qalog.write(configresults + '\n')
if arguments.w.upper() == 'Y':
print(\
'*****************************************************\n' + \
'*** Writing Running Config to Startup Config ***\n' + \
'*****************************************************\n')
qalog.write(\
'*****************************************************\n' + \
'*** Writing Running Config to Startup Config ***\n' + \
'*****************************************************\n')
configresults = conn.send_command('write mem')
print(configresults)
qalog.write(configresults)
print(\
'*****************************************************\n' + \
'*** Running show commands - after configurations ***\n' + \
'*****************************************************\n')
qalog.write(\
'*****************************************************\n' + \
'*** Running show commands - after configurations ***\n' + \
'*****************************************************\n')
if rw.get('Show_Commands') == rw.get('Show_Commands'):
logshowcommands(qalog, conn,
playbookinfo['ShowCommands'])
else:
logshowcommands(qalog, conn, SHOWCOMMANDS)
qalog.close()
conn.disconnect()
print('\n**** Task(s) Completed with no errors ****')
def main():
#creds = get_devinfo()
worksheets = {}
playbookinfo = {
'creds': {
'device_type': "",
'ip': "",
'username': "",
'password': "",
'secret': "ScHn31d3r"
},
'credsCore': {
'device_type': "",
'ip': "",
'username': "",
'password': "",
'secret': ""
},
'listofcommands':
["show run", "show vlan", "show int status", "show int trunk"]
}
with excel.ExcelFile("Cellar metering ports.xlsx") as wb:
for sname in wb.sheet_names:
print("print sheetname: ", sname)
readsheet = excel.read_excel(wb,
sheet_name=sname,
converters={
'Username': str,
'Password': str,
'Secret': str,
'data_type': str
})
df = DataFrame(data=readsheet, copy=True)
worksheets[sname] = df.to_dict(orient='records')
playbookinfo['creds']['username'] = getusername()
playbookinfo['creds']['password'] = getpassword(
playbookinfo['creds']['username'])
playbookinfo['credsCore']['username'] = playbookinfo['creds'][
'username']
playbookinfo['credsCore']['password'] = playbookinfo['creds'][
'password']
for rw in worksheets[sname]:
playbookinfo['creds']['device_type'] = 'cisco_ios'
playbookinfo['creds']['ip'] = rw.get('IP')
playbookinfo['credsCore']['ip'] = rw.get('CoreIP')
playbookinfo['credsCore']['device_type'] = playbookinfo[
'creds']['device_type']
portrange = str(rw.get('Metering'))
vlan = str(rw.get('VLAN'))
conn = connectToDevice(playbookinfo['creds'])
resultprompt = conn.find_prompt()
print('Processing device: ' + playbookinfo['creds']['ip'] +
'\n')
if resultprompt[len(resultprompt) - 1] != "#":
print("Changing from User mode to privilege mode\n" +
resultprompt)
conn.enable()
resultprompt = conn.find_prompt()
print(resultprompt)
else:
print("Already in privilege mode\n" + resultprompt)
qalog = openlogfile(resultprompt, playbookinfo['creds']['ip'])
qalog.write(get_logheader('Port(s) VLAN change - ' +
portrange))
# Log config before changes
qalog.write('********** BEFORE CHANGES ***********')
for cmd in playbookinfo['listofcommands']:
commandresults = conn.send_command(cmd)
qalog.write(get_logheader(cmd))
qalog.write(commandresults + '\n\n\n')
connC = connectToDevice(playbookinfo['credsCore'])
resultpromptC = connC.find_prompt()
for cmd in playbookinfo['listofcommands']:
commandresults = connC.send_command(cmd)
qalog.write(get_logheader(cmd))
qalog.write(commandresults + '\n\n\n')
#resultprompt = conn.config_mode()
print(resultprompt)
cmd = 'vlan ' + vlan + '\nname Metering-VLAN\n' + 'interface range ' + portrange + '\n' + 'switchport mode access\nswitchport access vlan ' \
+ vlan + '\ndescription *** Metering Port ***\nend\n'
# cmd = ['interface range ' + portrange, 'switchport mode access', 'switchport access vlan ' + vlan, 'description *** python changed ***']
commandresults = conn.send_config_set(config_commands=cmd)
qalog.write(commandresults + '\n\n\n')
cmd = 'interface ' + rw.get(
'IDFTrunk'
) + '\n' + 'switchport trunk allowed vlan add ' + vlan + '\n'
cmdC = 'interface ' + rw.get(
'CoreTrunk'
) + '\n' + 'switchport trunk allowed vlan add ' + vlan + '\n'
commandresults = conn.send_config_set(config_commands=cmd)
#print ('conf t results back =', commandresults)
print(resultprompt, '\n', commandresults)
print('Changing trunk config in Core: ' +
playbookinfo['credsCore']['ip'] + '\n')
commandresultsC = connC.send_config_set(config_commands=cmdC)
print(connC.find_prompt() + '\n' + commandresultsC + '\n')
qalog.write(commandresults + '\n\n\n')
qalog.write(commandresultsC + '\n\n\n')
commandresults = conn.send_command('wr mem')
qalog.write(get_logheader('Writing config changes'))
qalog.write(commandresults + '\n\n\n')
# Log config after changes
qalog.write('********** AFTER CHANGES ***********')
for cmd in playbookinfo['listofcommands']:
commandresults = conn.send_command(cmd)
qalog.write(get_logheader(cmd))
qalog.write(commandresults + '\n\n\n')
for cmd in playbookinfo['listofcommands']:
commandresults = connC.send_command(cmd)
qalog.write(get_logheader(cmd))
qalog.write(commandresults + '\n\n\n')
qalog.close()
conn.disconnect()
connC.disconnect()
print('Task Complete For: ' +
resultprompt[:len(resultprompt) - 1] + '\n\n')
def load_from_excel(excel_file, sheet, token):
df = read_excel(excel_file, sheet, index_col=None)
df = df.rename(columns={'Topic': 'anchor', 'Selector': 'label', 'Message': 'association'})
load_dataframe(df, sheet, token)
columns = list(psheet.iloc[start_row_num+1,:])
titles.append(psheet.iloc[start_row_num, 0])
end_row_num = start_row_num+1
while row_counts[end_row_num] > 0:
end_row_num += 1
table = pd.DataFrame(psheet.iloc[start_row_num+2:end_row_num,:])
table.index = range(end_row_num-start_row_num-2) # No title, no headers
table.columns = columns
table[columns[0]] = table[columns[0]].fillna(method="ffill")
table.replace("-", np.NaN, inplace=True)
if extend:
table["Geography"] = titles[-1]
tables.append(table)
return sheet_header, dict(zip(titles, tables))
pwb = read_excel("data/gpearnextime.xlsx", sheetname=None)
ws = pwb["8. GPMS Distribution"]
h, tt = extract_tables(ws)
if __name__ == "__main__":
import sys
# adul-crit-care-data-eng-apr-13-mar-14-tab.xls
pd.options.display.float_format = '{:,.0f}'.format
pwb = read_excel("data/gpearnextime.xlsx", sheetname=None)
wb = xl.load_workbook("data/gpearnextime.xlsx")
#pwb = read_excel("data/adul-crit-care-data-eng-apr-13-mar-14-tab.xlsx", sheetname=None)
#wb = xl.load_workbook("data/adul-crit-care-data-eng-apr-13-mar-14-tab.xlsx")
tot_tbls = 0
all_tables = {}
for sheet_name in wb.sheetnames:
if wb.get_sheet_by_name(sheet_name).sheet_state == "hidden":
from pandas.io.excel import read_excel
from numpy import mean
d = read_excel("e17data.xlsx","Sheet 1 - Table 1")
m1 = mean(d['age'])
m2 = mean(d['score'])
