x\c@sdZddlZddlmZmZmZmZddlmZddlm Z ddl Z ddl m Z ddl Z ddlZddljjZddljZddlmZmZmZmZmZmZmZmZddlmZdd lm Z m!Z!dd l"m#Z#m$Z$m%Z%m&Z&dd l'm(Z(dd l)m*Z*dd l+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1ddl2m3Z3ddl4m5Z5dddgZ6dddgZ7iZ8de dj9e:e,ddddZ;dZ<dZ=dZ>e e;e!dd e!d!d"d#d#e?e?e?e?e@e?e?e?e?e?e?e?e?eAe@e@e?e?e?d#d#eAeAd$ZBd%eCfd&YZDdeCfd'YZEd(ZFd)ZGd*ZHd+ZId,ZJd-ZKd.ZLd/ZMeejNdeCfd0YZOd1eOfd2YZPe<ePd3eOfd4YZQe<eQd5eCfd6YZRd7eOfd8YZSe<eSdS(9s Module parse to/from Excel iN(tdatetdatetimettimet timedelta(t LooseVersion(tUnsupportedOperation(tfill(t OrderedDictt add_metaclasstlrangetmaptranget string_typestutzip(tEmptyDataError(tAppendertdeprecate_kwarg(tis_booltis_floatt is_integert is_list_like(tconfig(t DataFrame(t _NA_VALUESt_is_urlt_stringify_patht_urlopent_validate_header_argtget_filepath_or_buffer(t pprint_thing(t TextParsert read_excelt ExcelWritert ExcelFiletxlsxtxlstxlsms Read an Excel file into a pandas DataFrame. Support both `xls` and `xlsx` file extensions from a local filesystem or URL. Support an option to read a single sheet or a list of sheets. Parameters ---------- io : str, file descriptor, pathlib.Path, ExcelFile or xlrd.Book The string could be a URL. Valid URL schemes include http, ftp, s3, gcs, and file. For file URLs, a host is expected. For instance, a local file could be /path/to/workbook.xlsx. sheet_name : str, int, list, or None, default 0 Strings are used for sheet names. Integers are used in zero-indexed sheet positions. Lists of strings/integers are used to request multiple sheets. Specify None to get all sheets. Available cases: * Defaults to ``0``: 1st sheet as a `DataFrame` * ``1``: 2nd sheet as a `DataFrame` * ``"Sheet1"``: Load sheet with name "Sheet1" * ``[0, 1, "Sheet5"]``: Load first, second and sheet named "Sheet5" as a dict of `DataFrame` * None: All sheets. header : int, list of int, default 0 Row (0-indexed) to use for the column labels of the parsed DataFrame. If a list of integers is passed those row positions will be combined into a ``MultiIndex``. Use None if there is no header. names : array-like, default None List of column names to use. If file contains no header row, then you should explicitly pass header=None. index_col : int, list of int, default None Column (0-indexed) to use as the row labels of the DataFrame. Pass None if there is no such column. If a list is passed, those columns will be combined into a ``MultiIndex``. If a subset of data is selected with ``usecols``, index_col is based on the subset. parse_cols : int or list, default None Alias of `usecols`. .. deprecated:: 0.21.0 Use `usecols` instead. usecols : int, str, list-like, or callable default None Return a subset of the columns. * If None, then parse all columns. * If int, then indicates last column to be parsed. .. deprecated:: 0.24.0 Pass in a list of int instead from 0 to `usecols` inclusive. * If str, then indicates comma separated list of Excel column letters and column ranges (e.g. "A:E" or "A,C,E:F"). Ranges are inclusive of both sides. * If list of int, then indicates list of column numbers to be parsed. * If list of string, then indicates list of column names to be parsed. .. versionadded:: 0.24.0 * If callable, then evaluate each column name against it and parse the column if the callable returns ``True``. .. versionadded:: 0.24.0 squeeze : bool, default False If the parsed data only contains one column then return a Series. dtype : Type name or dict of column -> type, default None Data type for data or columns. E.g. {'a': np.float64, 'b': np.int32} Use `object` to preserve data as stored in Excel and not interpret dtype. If converters are specified, they will be applied INSTEAD of dtype conversion. .. versionadded:: 0.20.0 engine : str, default None If io is not a buffer or path, this must be set to identify io. Acceptable values are None or xlrd. converters : dict, default None Dict of functions for converting values in certain columns. Keys can either be integers or column labels, values are functions that take one input argument, the Excel cell content, and return the transformed content. true_values : list, default None Values to consider as True. .. versionadded:: 0.19.0 false_values : list, default None Values to consider as False. .. versionadded:: 0.19.0 skiprows : list-like Rows to skip at the beginning (0-indexed). nrows : int, default None Number of rows to parse. .. versionadded:: 0.23.0 na_values : scalar, str, list-like, or dict, default None Additional strings to recognize as NA/NaN. If dict passed, specific per-column NA values. By default the following values are interpreted as NaN: 's', 'iFtsubsequent_indents s2'. keep_default_na : bool, default True If na_values are specified and keep_default_na is False the default NaN values are overridden, otherwise they're appended to. verbose : bool, default False Indicate number of NA values placed in non-numeric columns. parse_dates : bool, list-like, or dict, default False The behavior is as follows: * bool. If True -> try parsing the index. * list of int or names. e.g. If [1, 2, 3] -> try parsing columns 1, 2, 3 each as a separate date column. * list of lists. e.g. If [[1, 3]] -> combine columns 1 and 3 and parse as a single date column. * dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call result 'foo' If a column or index contains an unparseable date, the entire column or index will be returned unaltered as an object data type. For non-standard datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv`` Note: A fast-path exists for iso8601-formatted dates. date_parser : function, optional Function to use for converting a sequence of string columns to an array of datetime instances. The default uses ``dateutil.parser.parser`` to do the conversion. Pandas will try to call `date_parser` in three different ways, advancing to the next if an exception occurs: 1) Pass one or more arrays (as defined by `parse_dates`) as arguments; 2) concatenate (row-wise) the string values from the columns defined by `parse_dates` into a single array and pass that; and 3) call `date_parser` once for each row using one or more strings (corresponding to the columns defined by `parse_dates`) as arguments. thousands : str, default None Thousands separator for parsing string columns to numeric. Note that this parameter is only necessary for columns stored as TEXT in Excel, any numeric columns will automatically be parsed, regardless of display format. comment : str, default None Comments out remainder of line. Pass a character or characters to this argument to indicate comments in the input file. Any data between the comment string and the end of the current line is ignored. skip_footer : int, default 0 Alias of `skipfooter`. .. deprecated:: 0.23.0 Use `skipfooter` instead. skipfooter : int, default 0 Rows at the end to skip (0-indexed). convert_float : bool, default True Convert integral floats to int (i.e., 1.0 --> 1). If False, all numeric data will be read in as floats: Excel stores all numbers as floats internally. mangle_dupe_cols : bool, default True Duplicate columns will be specified as 'X', 'X.1', ...'X.N', rather than 'X'...'X'. Passing in False will cause data to be overwritten if there are duplicate names in the columns. **kwds : optional Optional keyword arguments can be passed to ``TextFileReader``. Returns ------- DataFrame or dict of DataFrames DataFrame from the passed in Excel file. See notes in sheet_name argument for more information on when a dict of DataFrames is returned. See Also -------- to_excel : Write DataFrame to an Excel file. to_csv : Write DataFrame to a comma-separated values (csv) file. read_csv : Read a comma-separated values (csv) file into DataFrame. read_fwf : Read a table of fixed-width formatted lines into DataFrame. Examples -------- The file can be read using the file name as string or an open file object: >>> pd.read_excel('tmp.xlsx', index_col=0) # doctest: +SKIP Name Value 0 string1 1 1 string2 2 2 #Comment 3 >>> pd.read_excel(open('tmp.xlsx', 'rb'), ... sheet_name='Sheet3') # doctest: +SKIP Unnamed: 0 Name Value 0 0 string1 1 1 1 string2 2 2 2 #Comment 3 Index and header can be specified via the `index_col` and `header` arguments >>> pd.read_excel('tmp.xlsx', index_col=None, header=None) # doctest: +SKIP 0 1 2 0 NaN Name Value 1 0.0 string1 1 2 1.0 string2 2 3 2.0 #Comment 3 Column types are inferred but can be explicitly specified >>> pd.read_excel('tmp.xlsx', index_col=0, ... dtype={'Name': str, 'Value': float}) # doctest: +SKIP Name Value 0 string1 1.0 1 string2 2.0 2 #Comment 3.0 True, False, and NA values, and thousands separators have defaults, but can be explicitly specified, too. Supply the values you would like as strings or lists of strings! >>> pd.read_excel('tmp.xlsx', index_col=0, ... na_values=['string1', 'string2']) # doctest: +SKIP Name Value 0 NaN 1 1 NaN 2 2 #Comment 3 Comment lines in the excel input file can be skipped using the `comment` kwarg >>> pd.read_excel('tmp.xlsx', index_col=0, comment='#') # doctest: +SKIP Name Value 0 string1 1.0 1 string2 2.0 2 None NaN cCstj|stdn|j}|t|= 1.0.0 for Excel supportiNs1.0.0s. Current version treadtseekit file_contentssCMust explicitly set engine if not passing in buffer or path for io.(txlrdR<t __VERSION__RRRRaR"tBookRtbookthasattrRgRRft open_workbookR*R R,(tselftfilepath_or_bufferterr_msgRit_tdata((s.lib/python2.7/site-packages/pandas/io/excel.pyt__init__|s6      cCs |jjS(N(Rlt sheet_names(Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRusic*( st|ddlmmmmm|jjfd}t }t |t r|}t }n-|dkr|jj}t }n |g}t tj|j}t}x|D]}| rdjd|GHnt |tjr"|jj|}n|jj|}g}t|}xgt|jD]V}gt|j||j|D]\}}|||^q~} |j| qVW|jdkrt||>> _range2cols('A:E') [0, 1, 2, 3, 4] >>> _range2cols('A,C,Z:AB') [0, 2, 25, 26, 27] t,t:ii(tsplittextendR RR5(tareastcolstrng((s.lib/python2.7/site-packages/pandas/io/excel.pyt _range2colss 1cCs`|dkr|St|r@tjdtddt|dSt|tjr\t |S|S(s Convert `usecols` into a compatible format for parsing in `parsers.py`. Parameters ---------- usecols : object The use-columns object to potentially convert. Returns ------- converted : object The compatible format of `usecols`. s|Passing in an integer for `usecols` has been deprecated. Please pass in a list of int from 0 to `usecols` inclusive instead.RFiiN( RRR\R]R^R RaR*R R(RB((s.lib/python2.7/site-packages/pandas/io/excel.pyR%s     cCsK|dk rGt|dkr8td|Dr8tStdntS(Nicss|]}t|tVqdS(N(RaR(t.0titem((s.lib/python2.7/site-packages/pandas/io/excel.pys GssLfreeze_panes must be of form (row, column) where row and column are integers(RRtallRR,R(t freeze_panes((s.lib/python2.7/site-packages/pandas/io/excel.pyt_validate_freeze_panesCs  cCsGx@t|dkrB|ddks5|ddkrB|d}qW|S(NiRi(RR(R((s.lib/python2.7/site-packages/pandas/io/excel.pyt_trim_excel_headerSs5cCstjrg}xmtt|D]P}t||tjrqy|jt||Wqrtk rmPqrXq"Pq"W|}n|S(s6 Convert elements in a row to string from Unicode. This is purely a Python 2.x patch and is performed ONLY when all elements of the row are string-like. Parameters ---------- row : array-like The row of data to convert. Returns ------- converted : array-like ( R*RR RRaR R5R4tUnicodeEncodeError(Rt convertedR((s.lib/python2.7/site-packages/pandas/io/excel.pyR[s   cCs|d}xutdt|D]^}||s=||}n||dks]||dkrj|||.writer``. NOTE: can only be passed as a keyword argument. date_format : string, default None Format string for dates written into Excel files (e.g. 'YYYY-MM-DD') datetime_format : string, default None Format string for datetime objects written into Excel files (e.g. 'YYYY-MM-DD HH:MM:SS') mode : {'w' or 'a'}, default 'w' File mode to use (write or append). .. versionadded:: 0.24.0 Attributes ---------- None Methods ------- None Notes ----- None of the methods and properties are considered public. For compatibility with CSV writers, ExcelWriter serializes lists and dicts to strings before writing. Examples -------- Default usage: >>> with ExcelWriter('path_to_file.xlsx') as writer: ... df.to_excel(writer) To write to separate sheets in a single file: >>> with ExcelWriter('path_to_file.xlsx') as writer: ... df1.to_excel(writer, sheet_name='Sheet1') ... df2.to_excel(writer, sheet_name='Sheet2') You can set the date format or datetime format: >>> with ExcelWriter('path_to_file.xlsx', date_format='YYYY-MM-DD', datetime_format='YYYY-MM-DD HH:MM:SS') as writer: ... df.to_excel(writer) You can also append to an existing Excel file: >>> with ExcelWriter('path_to_file.xlsx', mode='a') as writer: ... df.to_excel(writer, sheet_name='Sheet3') cKst|tr|dks6t|tr|dkrt|trbtjj|dd}nd}y:tj dj d|}|dkrt |}nWqt k rt dj d|}|qXnt|}ntj|S(NtautoiiR#sio.excel.{ext}.writerR(sNo engine for filetype: '{ext}'(t issubclassR!RRaR tostpathtsplitextRt get_optionR3R>R?R,R@tobjectt__new__(tclsRR-tkwargsR(terror((s.lib/python2.7/site-packages/pandas/io/excel.pyR s"       cCsdS(s&extensions that writer engine supportsN((Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyR/*scCsdS(sname of engineN((Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyR-/sicCsdS(s Write given formatted cells into Excel an excel sheet Parameters ---------- cells : generator cell of formatted data to save to Excel sheet sheet_name : string, default None Name of Excel sheet, if None, then use self.cur_sheet startrow : upper left cell row to dump data frame startcol : upper left cell column to dump data frame freeze_panes: integer tuple of length 2 contains the bottom-most row and right-most column to freeze N((RotcellsRHtstartrowtstartcolR((s.lib/python2.7/site-packages/pandas/io/excel.pyt write_cells4scCsdS(s( Save workbook to disk. N((Ro((s.lib/python2.7/site-packages/pandas/io/excel.pytsaveGstwcKst|tr(tjj|d}n|dkr:dnd}|j|||_i|_d|_|dkrd|_ n ||_ |dkrd|_ n ||_ ||_ dS(NiR:R$R#s YYYY-MM-DDsYYYY-MM-DD HH:MM:SS( RaR RRRtcheck_extensionRRt cur_sheett date_formattdatetime_formattmode(RoRR-RRRt engine_kwargsR(((s.lib/python2.7/site-packages/pandas/io/excel.pyRtNs          cCs t|jS(N(RR(Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRhscCs7|dkr|j}n|dkr3tdn|S(Ns7Must pass explicit sheet_name or set cur_sheet property(RRR,(RoRH((s.lib/python2.7/site-packages/pandas/io/excel.pyt_get_sheet_nameks    cCsd}t|r!t|}nt|r<t|}nt|rWt|}nst|trr|j }nXt|t r|j }n=t|t r|j td}d}ntj|}||fS(s>Convert numpy types to Python types for the Excel writers. Parameters ---------- val : object Value to be written into cells Returns ------- Tuple with the first element being the converted value and the second being an optional format iQt0N(RRRRtfloatRRRaRRRRRt total_secondsR*tto_str(RoRtfmt((s.lib/python2.7/site-packages/pandas/io/excel.pyt_value_with_fmtss       csjdrdntfd|jDswtdjdt|jdt}t|ntSdS(schecks that path's extension against the Writer's supported extensions. If it isn't supported, raises UnsupportedFiletypeError.R'ic3s|]}|kVqdS(N((Rt extension(R((s.lib/python2.7/site-packages/pandas/io/excel.pys ss0Invalid extension for engine '{engine}': '{ext}'R-R(N( R0tanyR/R R3RR-R,R(RR(tmsg((R(s.lib/python2.7/site-packages/pandas/io/excel.pyRs cCs|S(N((Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRscCs|jdS(N(R(RoRRR((s.lib/python2.7/site-packages/pandas/io/excel.pyRscCs |jS(s+synonym for save, to make it more file-like(R(Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRsN(RRRRRRlt curr_sheetRtabctabstractpropertyR/R-tabstractmethodRRRtRRRt classmethodRRRR(((s.lib/python2.7/site-packages/pandas/io/excel.pyR!s(?     !  t_OpenpyxlWritercBseZdZdZdddZdZedZedZ edZ ed Z ed Z ed Z ed Zed ZedZedZedZdddddZRS(R9s.xlsxs.xlsmRcKsddlm}tt|j|d|||jdkriddlm}||j}||_ ng||_ |j j ry|j j |j j dWqt k r|j j |j j dqXndS(Ni(tWorkbookRta(t load_workbooki(topenpyxl.workbookRtsuperRRtRR9RRRlt worksheetstremovetAttributeErrort remove_sheet(RoRR-RRRRRl((s.lib/python2.7/site-packages/pandas/io/excel.pyRts    cCs|jj|jS(s( Save workbook to disk. (RlRR(Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRscCsddlm}|}x{|jD]m\}}x^|jD]P\}}|dkrv|jj|jd|q?|j|j||q?Wq&W|S(s converts a style_dict to an openpyxl style object Parameters ---------- style_dict : style dictionary to convert i(tStyletborderst border_style(topenpyxl.styleR titemsR t__getattribute__t __setattr__(Rt style_dictR t xls_styletkeyRtnktnv((s.lib/python2.7/site-packages/pandas/io/excel.pyt_convert_to_styles    !cCsidd6}i}xs|jD]e\}}||krE||}nt|djd|d}||}|r |||s(RtgetattrR3(RRt_style_key_mapt style_kwargsRtvt _conv_to_xtnew_v((s.lib/python2.7/site-packages/pandas/io/excel.pyt_convert_to_style_kwargss     cCs7ddlm}t|tr)||S||SdS(s Convert ``color_spec`` to an openpyxl v2 Color object Parameters ---------- color_spec : str, dict A 32-bit ARGB hex string, or a dict with zero or more of the following keys. 'rgb' 'indexed' 'auto' 'theme' 'tint' 'index' 'type' Returns ------- color : openpyxl.styles.Color i(tColorN(topenpyxl.stylesR"RaR4(Rt color_specR"((s.lib/python2.7/site-packages/pandas/io/excel.pyt_convert_to_color s cCsddlm}idd6dd6dd6d d 6d d 6d d6}i}x[|jD]M\}}||krx||}n|dkr|j|}n|||ZRS(tnamet font_nameR(t font_sizeR'R1trgbt font_colorR*R)RR+R R,R.tfont_strikeoutR/t font_scriptR0tfontRdt num_formatRrtlockedthiddent protectiont horizontaltaligntverticaltvalignt text_rotationtrotationt wrap_textt text_wraptindentt shrink_to_fittshrinkt alignmentR;tpatternR<R:R=tfg_colorR>R?R@tbg_colorRARBRt border_colorRNRRZt top_colorRYt right_colorR[t bottom_colorRXt left_colorc Csdi}|d$k r||dR((R>RR(R?R((R?RR(R=((R=R(R>((R>R(R?((R?R(R@R((R@RR(RAR((RARR(RBR((RBRR(R@((R@R(RA((RAR(RB((RBR(R1R((R1RR(R1((R1R(RN((RNR(RZR1R((RZR1RR(RZR1((RZR1R(RZRN((RZRNRZ(RZ((RZRZ(RYR1R((RYR1RR(RYR1((RYR1R(RYRN((RYRNRY(RY((RYRY(R[R1R((R[R1RR(R[R1((R[R1R(R[RN((R[RNR[(R[((R[R[(RXR1R((RXR1RR(RXR1((RXR1R(RXRN((RXRNRX(RX((RXRXN(RRRRRR(((s.lib/python2.7/site-packages/pandas/io/excel.pyRsz      t _XlsxWritercBsGeZdZdZdddddZdZdddddZRS( R;s.xlsxRc Ksqddl}|dkr'tdntt|j|d|d|d|d|||j|||_dS(NiRs-Append mode is not supported with xlsxwriter!R-RRR(R;R,RRRtRRl(RoRR-RRRRR;((s.lib/python2.7/site-packages/pandas/io/excel.pyRts  cCs |jjS(s( Save workbook to disk. (RlR(Ro((s.lib/python2.7/site-packages/pandas/io/excel.pyRsic Cs|j|}||jkr.|j|}n|jj|}||j|R@RRRR RReR"RRRRRRRRtABCMetaR!RRRR(((s.lib/python2.7/site-packages/pandas/io/excel.pyts "   :".j%}     *u !    ! !   F