def _list_of_series_to_arrays(data, columns, coerce_float=False, dtype=None): if columns is None: columns = _get_objs_combined_axis(data, sort=False) indexer_cache = {} aligned_values = [] for s in data: index = getattr(s, 'index', None) if index is None: index = ibase.default_index(len(s)) if id(index) in indexer_cache: indexer = indexer_cache[id(index)] else: indexer = indexer_cache[id(index)] = index.get_indexer(columns) values = com.values_from_object(s) aligned_values.append(algorithms.take_1d(values, indexer)) values = np.vstack(aligned_values) if values.dtype == np.object_: content = list(values.T) return _convert_object_array(content, columns, dtype=dtype, coerce_float=coerce_float) else: return values.T, columns
def _list_of_series_to_arrays(data, columns, coerce_float=False, dtype=None): if columns is None: columns = _get_objs_combined_axis(data, sort=False) indexer_cache = {} aligned_values = [] for s in data: index = getattr(s, 'index', None) if index is None: index = ibase.default_index(len(s)) if id(index) in indexer_cache: indexer = indexer_cache[id(index)] else: indexer = indexer_cache[id(index)] = index.get_indexer(columns) values = com.values_from_object(s) aligned_values.append(algorithms.take_1d(values, indexer)) values = np.vstack(aligned_values) if values.dtype == np.object_: content = list(values.T) return _convert_object_array(content, columns, dtype=dtype, coerce_float=coerce_float) else: return values.T, columns
def _get_comb_axis(self, i): data_axis = self.objs[0]._get_block_manager_axis(i) try: return _get_objs_combined_axis(self.objs, axis=data_axis, intersect=self.intersect) except IndexError: types = [type(x).__name__ for x in self.objs] raise TypeError("Cannot concatenate list of %s" % types)
def _get_comb_axis(self, i): data_axis = self.objs[0]._get_block_manager_axis(i) try: return _get_objs_combined_axis( self.objs, axis=data_axis, intersect=self.intersect, sort=self.sort ) except IndexError: types = [type(x).__name__ for x in self.objs] raise TypeError("Cannot concatenate list of {types}".format(types=types))
def crosstab(index, columns, values=None, rownames=None, colnames=None, aggfunc=None, margins=False, margins_name='All', dropna=True, normalize=False): """ Compute a simple cross-tabulation of two (or more) factors. By default computes a frequency table of the factors unless an array of values and an aggregation function are passed Parameters ---------- index : array-like, Series, or list of arrays/Series Values to group by in the rows columns : array-like, Series, or list of arrays/Series Values to group by in the columns values : array-like, optional Array of values to aggregate according to the factors. Requires `aggfunc` be specified. aggfunc : function, optional If specified, requires `values` be specified as well rownames : sequence, default None If passed, must match number of row arrays passed colnames : sequence, default None If passed, must match number of column arrays passed margins : boolean, default False Add row/column margins (subtotals) margins_name : string, default 'All' Name of the row / column that will contain the totals when margins is True. .. versionadded:: 0.21.0 dropna : boolean, default True Do not include columns whose entries are all NaN normalize : boolean, {'all', 'index', 'columns'}, or {0,1}, default False Normalize by dividing all values by the sum of values. - If passed 'all' or `True`, will normalize over all values. - If passed 'index' will normalize over each row. - If passed 'columns' will normalize over each column. - If margins is `True`, will also normalize margin values. .. versionadded:: 0.18.1 Notes ----- Any Series passed will have their name attributes used unless row or column names for the cross-tabulation are specified. Any input passed containing Categorical data will have **all** of its categories included in the cross-tabulation, even if the actual data does not contain any instances of a particular category. In the event that there aren't overlapping indexes an empty DataFrame will be returned. Examples -------- >>> a = np.array(["foo", "foo", "foo", "foo", "bar", "bar", ... "bar", "bar", "foo", "foo", "foo"], dtype=object) >>> b = np.array(["one", "one", "one", "two", "one", "one", ... "one", "two", "two", "two", "one"], dtype=object) >>> c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny", ... "shiny", "dull", "shiny", "shiny", "shiny"], ... dtype=object) >>> pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c']) ... # doctest: +NORMALIZE_WHITESPACE b one two c dull shiny dull shiny a bar 1 2 1 0 foo 2 2 1 2 >>> foo = pd.Categorical(['a', 'b'], categories=['a', 'b', 'c']) >>> bar = pd.Categorical(['d', 'e'], categories=['d', 'e', 'f']) >>> crosstab(foo, bar) # 'c' and 'f' are not represented in the data, ... # but they still will be counted in the output ... # doctest: +SKIP col_0 d e f row_0 a 1 0 0 b 0 1 0 c 0 0 0 Returns ------- crosstab : DataFrame """ index = com._maybe_make_list(index) columns = com._maybe_make_list(columns) rownames = _get_names(index, rownames, prefix='row') colnames = _get_names(columns, colnames, prefix='col') common_idx = _get_objs_combined_axis(index + columns, intersect=True) data = {} data.update(zip(rownames, index)) data.update(zip(colnames, columns)) if values is None and aggfunc is not None: raise ValueError("aggfunc cannot be used without values.") if values is not None and aggfunc is None: raise ValueError("values cannot be used without an aggfunc.") from pandas import DataFrame df = DataFrame(data, index=common_idx) if values is None: df['__dummy__'] = 0 kwargs = {'aggfunc': len, 'fill_value': 0} else: df['__dummy__'] = values kwargs = {'aggfunc': aggfunc} table = df.pivot_table('__dummy__', index=rownames, columns=colnames, margins=margins, margins_name=margins_name, dropna=dropna, **kwargs) # Post-process if normalize is not False: table = _normalize(table, normalize=normalize, margins=margins, margins_name=margins_name) return table
def crosstab(index, columns, values=None, rownames=None, colnames=None, aggfunc=None, margins=False, margins_name='All', dropna=True, normalize=False): """ Compute a simple cross-tabulation of two (or more) factors. By default computes a frequency table of the factors unless an array of values and an aggregation function are passed Parameters ---------- index : array-like, Series, or list of arrays/Series Values to group by in the rows columns : array-like, Series, or list of arrays/Series Values to group by in the columns values : array-like, optional Array of values to aggregate according to the factors. Requires `aggfunc` be specified. aggfunc : function, optional If specified, requires `values` be specified as well rownames : sequence, default None If passed, must match number of row arrays passed colnames : sequence, default None If passed, must match number of column arrays passed margins : boolean, default False Add row/column margins (subtotals) margins_name : string, default 'All' Name of the row / column that will contain the totals when margins is True. .. versionadded:: 0.21.0 dropna : boolean, default True Do not include columns whose entries are all NaN normalize : boolean, {'all', 'index', 'columns'}, or {0,1}, default False Normalize by dividing all values by the sum of values. - If passed 'all' or `True`, will normalize over all values. - If passed 'index' will normalize over each row. - If passed 'columns' will normalize over each column. - If margins is `True`, will also normalize margin values. .. versionadded:: 0.18.1 Notes ----- Any Series passed will have their name attributes used unless row or column names for the cross-tabulation are specified. Any input passed containing Categorical data will have **all** of its categories included in the cross-tabulation, even if the actual data does not contain any instances of a particular category. In the event that there aren't overlapping indexes an empty DataFrame will be returned. Examples -------- >>> a = np.array(["foo", "foo", "foo", "foo", "bar", "bar", ... "bar", "bar", "foo", "foo", "foo"], dtype=object) >>> b = np.array(["one", "one", "one", "two", "one", "one", ... "one", "two", "two", "two", "one"], dtype=object) >>> c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny", ... "shiny", "dull", "shiny", "shiny", "shiny"], ... dtype=object) >>> pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c']) ... # doctest: +NORMALIZE_WHITESPACE b one two c dull shiny dull shiny a bar 1 2 1 0 foo 2 2 1 2 >>> foo = pd.Categorical(['a', 'b'], categories=['a', 'b', 'c']) >>> bar = pd.Categorical(['d', 'e'], categories=['d', 'e', 'f']) >>> crosstab(foo, bar) # 'c' and 'f' are not represented in the data, # and will not be shown in the output because # dropna is True by default. Set 'dropna=False' # to preserve categories with no data ... # doctest: +SKIP col_0 d e row_0 a 1 0 b 0 1 >>> crosstab(foo, bar, dropna=False) # 'c' and 'f' are not represented # in the data, but they still will be counted # and shown in the output ... # doctest: +SKIP col_0 d e f row_0 a 1 0 0 b 0 1 0 c 0 0 0 Returns ------- crosstab : DataFrame """ index = com.maybe_make_list(index) columns = com.maybe_make_list(columns) rownames = _get_names(index, rownames, prefix='row') colnames = _get_names(columns, colnames, prefix='col') common_idx = _get_objs_combined_axis(index + columns, intersect=True, sort=False) data = {} data.update(zip(rownames, index)) data.update(zip(colnames, columns)) if values is None and aggfunc is not None: raise ValueError("aggfunc cannot be used without values.") if values is not None and aggfunc is None: raise ValueError("values cannot be used without an aggfunc.") from pandas import DataFrame df = DataFrame(data, index=common_idx) if values is None: df['__dummy__'] = 0 kwargs = {'aggfunc': len, 'fill_value': 0} else: df['__dummy__'] = values kwargs = {'aggfunc': aggfunc} table = df.pivot_table('__dummy__', index=rownames, columns=colnames, margins=margins, margins_name=margins_name, dropna=dropna, **kwargs) # Post-process if normalize is not False: table = _normalize(table, normalize=normalize, margins=margins, margins_name=margins_name) return table