In [1]:
import pandas
In [2]:
print dir(pandas)
['Categorical', 'CategoricalIndex', 'DataFrame', 'DateOffset', 'DatetimeIndex', 'ExcelFile', 'ExcelWriter', 'Expr', 'Float64Index', 'Grouper', 'HDFStore', 'Index', 'IndexSlice', 'Int64Index', 'Interval', 'IntervalIndex', 'MultiIndex', 'NaT', 'Panel', 'Panel4D', 'Period', 'PeriodIndex', 'RangeIndex', 'Series', 'SparseArray', 'SparseDataFrame', 'SparseList', 'SparseSeries', 'Term', 'TimeGrouper', 'Timedelta', 'TimedeltaIndex', 'Timestamp', 'UInt64Index', 'WidePanel', '_DeprecatedModule', '__builtins__', '__doc__', '__docformat__', '__file__', '__name__', '__package__', '__path__', '__version__', '_hashtable', '_lib', '_libs', '_np_version_under1p10', '_np_version_under1p11', '_np_version_under1p12', '_np_version_under1p13', '_np_version_under1p14', '_np_version_under1p15', '_tslib', '_version', 'api', 'bdate_range', 'compat', 'concat', 'core', 'crosstab', 'cut', 'date_range', 'datetime', 'datetools', 'describe_option', 'errors', 'eval', 'ewma', 'ewmcorr', 'ewmcov', 'ewmstd', 'ewmvar', 'ewmvol', 'expanding_apply', 'expanding_corr', 'expanding_count', 'expanding_cov', 'expanding_kurt', 'expanding_max', 'expanding_mean', 'expanding_median', 'expanding_min', 'expanding_quantile', 'expanding_skew', 'expanding_std', 'expanding_sum', 'expanding_var', 'factorize', 'get_dummies', 'get_option', 'get_store', 'groupby', 'infer_freq', 'interval_range', 'io', 'isna', 'isnull', 'json', 'lib', 'lreshape', 'match', 'melt', 'merge', 'merge_asof', 'merge_ordered', 'notna', 'notnull', 'np', 'offsets', 'option_context', 'options', 'ordered_merge', 'pandas', 'parser', 'period_range', 'pivot', 'pivot_table', 'plot_params', 'plotting', 'pnow', 'qcut', 'read_clipboard', 'read_csv', 'read_excel', 'read_feather', 'read_fwf', 'read_gbq', 'read_hdf', 'read_html', 'read_json', 'read_msgpack', 'read_parquet', 'read_pickle', 'read_sas', 'read_sql', 'read_sql_query', 'read_sql_table', 'read_stata', 'read_table', 'reset_option', 'rolling_apply', 'rolling_corr', 'rolling_count', 'rolling_cov', 'rolling_kurt', 'rolling_max', 'rolling_mean', 'rolling_median', 'rolling_min', 'rolling_quantile', 'rolling_skew', 'rolling_std', 'rolling_sum', 'rolling_var', 'rolling_window', 'scatter_matrix', 'set_eng_float_format', 'set_option', 'show_versions', 'stats', 'test', 'testing', 'timedelta_range', 'to_datetime', 'to_msgpack', 'to_numeric', 'to_pickle', 'to_timedelta', 'tools', 'tseries', 'tslib', 'unique', 'util', 'value_counts', 'wide_to_long']
In [14]:
pd = pandas.DataFrame([[1,2,3], [4,5,6,7]])
In [15]:
pd
Out[15]:
0
1
2
3
0
1
2
3
NaN
1
4
5
6
7.0
In [18]:
a = {'a':"python", "b":"Java", "c":"Jenkins"}
b = {'a':"python", "b":".net"}
pd = pandas.DataFrame([a,b])
In [19]:
pd
Out[19]:
a
b
c
0
python
Java
Jenkins
1
python
.net
NaN
In [20]:
pd = pandas.DataFrame([[1,2,3], [4,5,6,7]])
In [21]:
pd
Out[21]:
0
1
2
3
0
1
2
3
NaN
1
4
5
6
7.0
In [26]:
x = pandas.DataFrame([[1,2,3], [4,5,6,7]], columns=['fir', 'sec', 'thi', 'four'])
In [27]:
x
Out[27]:
fir
sec
thi
four
0
1
2
3
NaN
1
4
5
6
7.0
In [30]:
x = pandas.DataFrame([[1,2,3], [4,5,6,7]], columns=['fir', 'sec', 'thi', 'four'], index=['row1', 'row2'])
In [31]:
x
Out[31]:
fir
sec
thi
four
row1
1
2
3
NaN
row2
4
5
6
7.0
In [32]:
type(x)
Out[32]:
pandas.core.frame.DataFrame
In [33]:
print dir(x)
['T', '_AXIS_ALIASES', '_AXIS_IALIASES', '_AXIS_LEN', '_AXIS_NAMES', '_AXIS_NUMBERS', '_AXIS_ORDERS', '_AXIS_REVERSED', '_AXIS_SLICEMAP', '__abs__', '__add__', '__and__', '__array__', '__array_wrap__', '__bool__', '__bytes__', '__class__', '__contains__', '__copy__', '__deepcopy__', '__delattr__', '__delitem__', '__dict__', '__dir__', '__div__', '__doc__', '__eq__', '__finalize__', '__floordiv__', '__format__', '__ge__', '__getattr__', '__getattribute__', '__getitem__', '__getstate__', '__gt__', '__hash__', '__iadd__', '__iand__', '__idiv__', '__ifloordiv__', '__imod__', '__imul__', '__init__', '__invert__', '__ior__', '__ipow__', '__isub__', '__iter__', '__itruediv__', '__ixor__', '__le__', '__len__', '__lt__', '__mod__', '__module__', '__mul__', '__ne__', '__neg__', '__new__', '__nonzero__', '__or__', '__pow__', '__radd__', '__rand__', '__rdiv__', '__reduce__', '__reduce_ex__', '__repr__', '__rfloordiv__', '__rmod__', '__rmul__', '__ror__', '__round__', '__rpow__', '__rsub__', '__rtruediv__', '__rxor__', '__setattr__', '__setitem__', '__setstate__', '__sizeof__', '__str__', '__sub__', '__subclasshook__', '__truediv__', '__unicode__', '__weakref__', '__xor__', '_accessors', '_add_numeric_operations', '_add_series_only_operations', '_add_series_or_dataframe_operations', '_agg_by_level', '_agg_doc', '_aggregate', '_aggregate_multiple_funcs', '_align_frame', '_align_series', '_apply_broadcast', '_apply_empty_result', '_apply_raw', '_apply_standard', '_at', '_box_col_values', '_box_item_values', '_builtin_table', '_check_inplace_setting', '_check_is_chained_assignment_possible', '_check_percentile', '_check_setitem_copy', '_clear_item_cache', '_clip_with_one_bound', '_clip_with_scalar', '_combine_const', '_combine_frame', '_combine_match_columns', '_combine_match_index', '_combine_series', '_combine_series_infer', '_compare_frame', '_compare_frame_evaluate', '_consolidate', '_consolidate_inplace', '_construct_axes_dict', '_construct_axes_dict_for_slice', '_construct_axes_dict_from', '_construct_axes_from_arguments', '_constructor', '_constructor_expanddim', '_constructor_sliced', '_convert', '_count_level', '_create_indexer', '_cython_table', '_deprecations', '_dir_additions', '_dir_deletions', '_drop_axis', '_ensure_valid_index', '_expand_axes', '_flex_compare_frame', '_from_arrays', '_from_axes', '_get_agg_axis', '_get_axis', '_get_axis_name', '_get_axis_number', '_get_axis_resolvers', '_get_block_manager_axis', '_get_bool_data', '_get_cacher', '_get_index_resolvers', '_get_item_cache', '_get_numeric_data', '_get_valid_indices', '_get_value', '_get_values', '_getitem_array', '_getitem_column', '_getitem_frame', '_getitem_multilevel', '_getitem_slice', '_gotitem', '_iat', '_iget_item_cache', '_iloc', '_indexed_same', '_info_axis', '_info_axis_name', '_info_axis_number', '_info_repr', '_init_dict', '_init_mgr', '_init_ndarray', '_internal_names', '_internal_names_set', '_is_builtin_func', '_is_cached', '_is_cython_func', '_is_datelike_mixed_type', '_is_mixed_type', '_is_numeric_mixed_type', '_is_view', '_ix', '_ixs', '_join_compat', '_loc', '_maybe_cache_changed', '_maybe_update_cacher', '_metadata', '_needs_reindex_multi', '_obj_with_exclusions', '_protect_consolidate', '_reduce', '_reindex_axes', '_reindex_axis', '_reindex_columns', '_reindex_index', '_reindex_multi', '_reindex_with_indexers', '_repr_data_resource_', '_repr_fits_horizontal_', '_repr_fits_vertical_', '_repr_html_', '_repr_latex_', '_reset_cache', '_reset_cacher', '_sanitize_column', '_selected_obj', '_selection', '_selection_list', '_selection_name', '_series', '_set_as_cached', '_set_axis', '_set_axis_name', '_set_is_copy', '_set_item', '_set_value', '_setitem_array', '_setitem_frame', '_setitem_slice', '_setup_axes', '_shallow_copy', '_slice', '_stat_axis', '_stat_axis_name', '_stat_axis_number', '_take', '_to_dict_of_blocks', '_try_aggregate_string_function', '_typ', '_unpickle_frame_compat', '_unpickle_matrix_compat', '_update_inplace', '_validate_dtype', '_values', '_where', '_xs', 'abs', 'add', 'add_prefix', 'add_suffix', 'agg', 'aggregate', 'align', 'all', 'any', 'append', 'apply', 'applymap', 'as_matrix', 'asfreq', 'asof', 'assign', 'astype', 'at', 'at_time', 'axes', 'between_time', 'bfill', 'bool', 'boxplot', 'clip', 'clip_lower', 'clip_upper', 'columns', 'combine', 'combine_first', 'compound', 'copy', 'corr', 'corrwith', 'count', 'cov', 'cummax', 'cummin', 'cumprod', 'cumsum', 'describe', 'diff', 'div', 'divide', 'dot', 'drop', 'drop_duplicates', 'dropna', 'dtypes', 'duplicated', 'empty', 'eq', 'equals', 'eval', 'ewm', 'expanding', 'ffill', 'fillna', 'filter', 'fir', 'first', 'first_valid_index', 'floordiv', 'four', 'from_dict', 'from_items', 'from_records', 'ftypes', 'ge', 'get', 'get_dtype_counts', 'get_ftype_counts', 'get_values', 'groupby', 'gt', 'head', 'hist', 'iat', 'idxmax', 'idxmin', 'iloc', 'index', 'infer_objects', 'info', 'insert', 'interpolate', 'is_copy', 'isin', 'isna', 'isnull', 'items', 'iteritems', 'iterrows', 'itertuples', 'ix', 'join', 'keys', 'kurt', 'kurtosis', 'last', 'last_valid_index', 'le', 'loc', 'lookup', 'lt', 'mad', 'mask', 'max', 'mean', 'median', 'melt', 'memory_usage', 'merge', 'min', 'mod', 'mode', 'mul', 'multiply', 'ndim', 'ne', 'nlargest', 'notna', 'notnull', 'nsmallest', 'nunique', 'pct_change', 'pipe', 'pivot', 'pivot_table', 'plot', 'pop', 'pow', 'prod', 'product', 'quantile', 'query', 'radd', 'rank', 'rdiv', 'reindex', 'reindex_axis', 'reindex_like', 'rename', 'rename_axis', 'reorder_levels', 'replace', 'resample', 'reset_index', 'rfloordiv', 'rmod', 'rmul', 'rolling', 'round', 'rpow', 'rsub', 'rtruediv', 'sample', 'sec', 'select', 'select_dtypes', 'sem', 'set_axis', 'set_index', 'shape', 'shift', 'size', 'skew', 'slice_shift', 'sort_index', 'sort_values', 'squeeze', 'stack', 'std', 'style', 'sub', 'subtract', 'sum', 'swapaxes', 'swaplevel', 'tail', 'take', 'thi', 'to_clipboard', 'to_csv', 'to_dense', 'to_dict', 'to_excel', 'to_feather', 'to_gbq', 'to_hdf', 'to_html', 'to_json', 'to_latex', 'to_msgpack', 'to_panel', 'to_parquet', 'to_period', 'to_pickle', 'to_records', 'to_sparse', 'to_sql', 'to_stata', 'to_string', 'to_timestamp', 'to_xarray', 'transform', 'transpose', 'truediv', 'truncate', 'tshift', 'tz_convert', 'tz_localize', 'unstack', 'update', 'values', 'var', 'where', 'xs']
In [35]:
x.shape
Out[35]:
(2, 4)
In [36]:
x.transpose()
Out[36]:
row1
row2
fir
1.0
4.0
sec
2.0
5.0
thi
3.0
6.0
four
NaN
7.0
In [37]:
x[]
Out[37]:
fir
sec
thi
four
row1
1
2
3
NaN
row2
4
5
6
7.0
In [38]:
x
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-38-2f755f117ac9> in <module>()
----> 1 x[0]
c:\python27\lib\site-packages\pandas\core\frame.pyc in __getitem__(self, key)
2137 return self._getitem_multilevel(key)
2138 else:
-> 2139 return self._getitem_column(key)
2140
2141 def _getitem_column(self, key):
c:\python27\lib\site-packages\pandas\core\frame.pyc in _getitem_column(self, key)
2144 # get column
2145 if self.columns.is_unique:
-> 2146 return self._get_item_cache(key)
2147
2148 # duplicate columns & possible reduce dimensionality
c:\python27\lib\site-packages\pandas\core\generic.pyc in _get_item_cache(self, item)
1840 res = cache.get(item)
1841 if res is None:
-> 1842 values = self._data.get(item)
1843 res = self._box_item_values(item, values)
1844 cache[item] = res
c:\python27\lib\site-packages\pandas\core\internals.pyc in get(self, item, fastpath)
3836
3837 if not isna(item):
-> 3838 loc = self.items.get_loc(item)
3839 else:
3840 indexer = np.arange(len(self.items))[isna(self.items)]
c:\python27\lib\site-packages\pandas\core\indexes\base.pyc in get_loc(self, key, method, tolerance)
2522 return self._engine.get_loc(key)
2523 except KeyError:
-> 2524 return self._engine.get_loc(self._maybe_cast_indexer(key))
2525
2526 indexer = self.get_indexer([key], method=method, tolerance=tolerance)
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()
KeyError: 0
In [39]:
x
Out[39]:
fir
sec
thi
four
row1
1
2
3
NaN
row2
4
5
6
7.0
In [41]:
x.drop('row2')
Out[41]:
fir
sec
thi
four
row1
1
2
3
NaN
In [44]:
print str(pandas.read_excel.__doc__)
Read an Excel table into a pandas DataFrame
Parameters
----------
io : string, path object (pathlib.Path or py._path.local.LocalPath),
file-like object, pandas ExcelFile, or xlrd workbook.
The string could be a URL. Valid URL schemes include http, ftp, s3,
and file. For file URLs, a host is expected. For instance, a local
file could be file://localhost/path/to/workbook.xlsx
sheet_name : string, int, mixed list of strings/ints, 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.
str|int -> DataFrame is returned.
list|None -> Dict of DataFrames is returned, with keys representing
sheets.
Available Cases
* Defaults to 0 -> 1st sheet as a DataFrame
* 1 -> 2nd sheet as a DataFrame
* "Sheet1" -> 1st sheet as a DataFrame
* [0,1,"Sheet5"] -> 1st, 2nd & 5th sheet as a dictionary of DataFrames
* None -> All sheets as a dictionary of DataFrames
sheetname : string, int, mixed list of strings/ints, or None, default 0
.. deprecated:: 0.21.0
Use `sheet_name` instead
header : int, list of ints, 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.
skiprows : list-like
Rows to skip at the beginning (0-indexed)
skip_footer : int, default 0
Rows at the end to skip (0-indexed)
index_col : int, list of ints, 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.
names : array-like, default None
List of column names to use. If file contains no header row,
then you should explicitly pass header=None
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.
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
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
parse_cols : int or list, default None
.. deprecated:: 0.21.0
Pass in `usecols` instead.
usecols : int or list, default None
* If None then parse all columns,
* If int then indicates last column to be parsed
* If list of ints then indicates list of column numbers to be parsed
* If string 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.
squeeze : boolean, default False
If the parsed data only contains one column then return a Series
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: '', '#N/A', '#N/A N/A', '#NA', '-1.#IND', '-1.#QNAN', '-NaN', '-nan',
'1.#IND', '1.#QNAN', 'N/A', 'NA', 'NULL', 'NaN', 'n/a', 'nan', 'null'.
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.
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 : boolean, default False
Indicate number of NA values placed in non-numeric columns
engine: string, default None
If io is not a buffer or path, this must be set to identify io.
Acceptable values are None or xlrd
convert_float : boolean, 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
Returns
-------
parsed : 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.
In [50]:
x = pandas.read_excel('excel.xlsx', sheetname=0)
In [51]:
x
Out[51]:
sub
time
batch
location
faculty
0
python
08:30:00
1
hyderabad
Nag
1
python
08:30:00
2
hyderabad
Nag
2
python
08:30:00
1
Chennai
Nag
3
AWS
07:30:00
1
hyderabad
xxxxx
In [52]:
x=x.transpose()
In [55]:
x
Out[55]:
0
1
2
3
sub
python
python
python
AWS
time
08:30:00
08:30:00
08:30:00
07:30:00
batch
1
2
1
1
location
hyderabad
hyderabad
Chennai
hyderabad
faculty
Nag
Nag
Nag
xxxxx
In [56]:
x['ID']=[i+1 for i in xrange(len(x.index))]
In [57]:
x
Out[57]:
0
1
2
3
ID
sub
python
python
python
AWS
1
time
08:30:00
08:30:00
08:30:00
07:30:00
2
batch
1
2
1
1
3
location
hyderabad
hyderabad
Chennai
hyderabad
4
faculty
Nag
Nag
Nag
xxxxx
5
In [58]:
x.set_index('ID')
Out[58]:
0
1
2
3
ID
1
python
python
python
AWS
2
08:30:00
08:30:00
08:30:00
07:30:00
3
1
2
1
1
4
hyderabad
hyderabad
Chennai
hyderabad
5
Nag
Nag
Nag
xxxxx
In [ ]:
Content source: nageswau/python_class
Similar notebooks: