In [9]:
import pandas as pd
import os
In [10]:
files = os.listdir('../raw_data')
In [11]:
data = {f: pd.read_excel('../raw_data/'+f) for f in files }
---------------------------------------------------------------------------
XLRDError Traceback (most recent call last)
<ipython-input-11-16ab705ff402> in <module>()
----> 1 data = {f: pd.read_excel('../raw_data/'+f) for f in files }
<ipython-input-11-16ab705ff402> in <dictcomp>(.0)
----> 1 data = {f: pd.read_excel('../raw_data/'+f) for f in files }
/home/larry/envs/cityview/lib/python3.5/site-packages/pandas/io/excel.py in read_excel(io, sheetname, header, skiprows, skip_footer, index_col, names, parse_cols, parse_dates, date_parser, na_values, thousands, convert_float, has_index_names, converters, true_values, false_values, engine, squeeze, **kwds)
189
190 if not isinstance(io, ExcelFile):
--> 191 io = ExcelFile(io, engine=engine)
192
193 return io._parse_excel(
/home/larry/envs/cityview/lib/python3.5/site-packages/pandas/io/excel.py in __init__(self, io, **kwds)
247 self.book = xlrd.open_workbook(file_contents=data)
248 elif isinstance(io, compat.string_types):
--> 249 self.book = xlrd.open_workbook(io)
250 else:
251 raise ValueError('Must explicitly set engine if not passing in'
/home/larry/envs/cityview/lib/python3.5/site-packages/xlrd/__init__.py in open_workbook(filename, logfile, verbosity, use_mmap, file_contents, encoding_override, formatting_info, on_demand, ragged_rows)
439 formatting_info=formatting_info,
440 on_demand=on_demand,
--> 441 ragged_rows=ragged_rows,
442 )
443 return bk
/home/larry/envs/cityview/lib/python3.5/site-packages/xlrd/book.py in open_workbook_xls(filename, logfile, verbosity, use_mmap, file_contents, encoding_override, formatting_info, on_demand, ragged_rows)
89 t1 = time.clock()
90 bk.load_time_stage_1 = t1 - t0
---> 91 biff_version = bk.getbof(XL_WORKBOOK_GLOBALS)
92 if not biff_version:
93 raise XLRDError("Can't determine file's BIFF version")
/home/larry/envs/cityview/lib/python3.5/site-packages/xlrd/book.py in getbof(self, rqd_stream)
1228 bof_error('Expected BOF record; met end of file')
1229 if opcode not in bofcodes:
-> 1230 bof_error('Expected BOF record; found %r' % self.mem[savpos:savpos+8])
1231 length = self.get2bytes()
1232 if length == MY_EOF:
/home/larry/envs/cityview/lib/python3.5/site-packages/xlrd/book.py in bof_error(msg)
1222 if DEBUG: print("reqd: 0x%04x" % rqd_stream, file=self.logfile)
1223 def bof_error(msg):
-> 1224 raise XLRDError('Unsupported format, or corrupt file: ' + msg)
1225 savpos = self._position
1226 opcode = self.get2bytes()
XLRDError: Unsupported format, or corrupt file: Expected BOF record; found b',larry,p'
In [ ]:
parking = data['Hack4Cause_Parking Citations FY 2008.xls']
parking.columns
In [ ]:
clean = parking.dropna(how='all')
clean
In [ ]:
%load_ext sql
%sql "postgresql://cityview:testthis@localhost/cityview"
In [ ]:
Content source: civiclee/Hack4Cause2017
Similar notebooks: