Python types.is_string_dtype方法代码示例

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def generate_plotly_dim_dict(df, field):
    dim_dict = {}
    dim_dict["label"] = field
    column = df[field]
    if is_numeric_dtype(column):
        dim_dict["values"] = column
    elif is_string_dtype(column):
        texts = column.unique()
        dim_dict["values"] = [
            np.argwhere(texts == x).flatten()[0] for x in column
        ]
        dim_dict["tickvals"] = list(range(len(texts)))
        dim_dict["ticktext"] = texts
    else:
        raise Exception("Unidentifiable Type")

    return dim_dict 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def fit(self, X, y):
        """Fit the Imputer to the dataset and determine the right approach.

        Args:
            X (pd.Series): Dataset to fit the imputer, or predictors
            y (pd.Series): None, or dataset to fit predictors

        Returns:
            self. Instance of the class.
        """
        # start off with stats blank
        stats = {"param": None, "strategy": None}

        # if y is None, fitting simply X. univariate method.
        if y is None:
            if is_numeric_dtype(X):
                stats = {"param": self.num_imputer.fit(X, y),
                         "strategy": self.num_imputer.strategy}
            if is_string_dtype(X):
                stats = {"param": self.cat_imputer.fit(X, y),
                         "strategy": self.cat_imputer.strategy}

        # if y is not None, fitting X to y. predictive method.
        if not y is None:
            if is_numeric_dtype(y):
                stats = {"param": self.num_imputer.fit(X, y),
                         "strategy": self.num_imputer.strategy}
            if is_string_dtype(y):
                stats = {"param": self.cat_imputer.fit(X, y),
                         "strategy": self.cat_imputer.strategy}

        # return final stats
        self.statistics_ = stats
        return self 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def _not_cat_series(m, s):
    """Private method to detect Series that are not categorical."""
    if not is_string_dtype(s):
        t = s.dtype
        err = f"{m} not appropriate for Series {s.name} of type {t}."
        raise TypeError(err) 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def strings_to_categoricals(adata):
    """Transform string annotations to categoricals.
    """
    from pandas.api.types import is_string_dtype, is_integer_dtype, is_bool_dtype
    from pandas import Categorical

    def is_valid_dtype(values):
        return (
            is_string_dtype(values) or is_integer_dtype(values) or is_bool_dtype(values)
        )

    df = adata.obs
    df_keys = [key for key in df.columns if is_valid_dtype(df[key])]
    for key in df_keys:
        c = df[key]
        c = Categorical(c)
        if 1 < len(c.categories) < min(len(c), 100):
            df[key] = c

    df = adata.var
    df_keys = [key for key in df.columns if is_string_dtype(df[key])]
    for key in df_keys:
        c = df[key]
        c = Categorical(c)
        if 1 < len(c.categories) < min(len(c), 100):
            df[key] = c 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def _(anno, length, index_names):
    anno = anno.copy()
    if not is_string_dtype(anno.index):
        warnings.warn("Transforming to str index.", ImplicitModificationWarning)
        anno.index = anno.index.astype(str)
    return anno 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def strings_to_categoricals(self, df: Optional[pd.DataFrame] = None):
        """\
        Transform string annotations to categoricals.

        Only affects string annotations that lead to less categories than the
        total number of observations.

        Params
        ------
        df
            If `df` is `None`, modifies both :attr:`obs` and :attr:`var`,
            otherwise modifies `df` inplace.

        Notes
        -----
        Turns the view of an :class:`~anndata.AnnData` into an actual
        :class:`~anndata.AnnData`.
        """
        dont_modify = False  # only necessary for backed views
        if df is None:
            dfs = [self.obs, self.var]
            if self.is_view and self.isbacked:
                dont_modify = True
        else:
            dfs = [df]
        for df in dfs:
            string_cols = [
                key
                for key in df.columns
                if is_string_dtype(df[key]) and not is_categorical(df[key])
            ]
            for key in string_cols:
                # make sure we only have strings
                # (could be that there are np.nans (float), -666, "-666", for instance)
                c = df[key].astype("U")
                # make a categorical
                c = pd.Categorical(c, categories=natsorted(np.unique(c)))
                if len(c.categories) >= len(c):
                    continue
                if dont_modify:
                    raise RuntimeError(
                        "Please call `.strings_to_categoricals()` on full "
                        "AnnData, not on this view. You might encounter this"
                        "error message while copying or writing to disk."
                    )
                if self.is_view:
                    warnings.warn(
                        "Initializing view as actual.", ImplicitModificationWarning
                    )
                # If `self` is a view, it will be actualized in the next line,
                # therefore the previous warning
                df[key] = c
                logger.info(f"... storing {key!r} as categorical") 

# 需要导入模块: from pandas.api import types [as 别名]
# 或者: from pandas.api.types import is_string_dtype [as 别名]
def woepoints_ply1(dtx, binx, x_i, woe_points):
    '''
    Transform original values into woe or porints for one variable.
    
    Params
    ------
    
    Returns
    ------
    
    '''
    # woe_points: "woe" "points"
    # binx = bins.loc[lambda x: x.variable == x_i] 
    # https://stackoverflow.com/questions/12680754/split-explode-pandas-dataframe-string-entry-to-separate-rows
    binx = pd.merge(
      binx[['bin']].assign(v1=binx['bin'].str.split('%,%')).explode('v1'),
      binx[['bin', woe_points]],
      how='left', on='bin'
    ).rename(columns={'v1':'V1',woe_points:'V2'})
    
    # dtx
    ## cut numeric variable
    if is_numeric_dtype(dtx[x_i]):
        is_sv = pd.Series(not bool(re.search(r'\[', str(i))) for i in binx.V1)
        binx_sv = binx.loc[is_sv]
        binx_other = binx.loc[~is_sv]
        # create bin column
        breaks_binx_other = np.unique(list(map(float, ['-inf']+[re.match(r'.*\[(.*),.+\).*', str(i)).group(1) for i in binx_other['bin']]+['inf'])))
        labels = ['[{},{})'.format(breaks_binx_other[i], breaks_binx_other[i+1]) for i in range(len(breaks_binx_other)-1)]
        
        dtx = dtx.assign(xi_bin = lambda x: pd.cut(x[x_i], breaks_binx_other, right=False, labels=labels))\
          .assign(xi_bin = lambda x: [i if (i != i) else str(i) for i in x['xi_bin']])
        # dtx.loc[:,'xi_bin'] = pd.cut(dtx[x_i], breaks_binx_other, right=False, labels=labels)
        # dtx.loc[:,'xi_bin'] = np.where(pd.isnull(dtx['xi_bin']), dtx['xi_bin'], dtx['xi_bin'].astype(str))
        #
        mask = dtx[x_i].isin(binx_sv['V1'])
        dtx.loc[mask,'xi_bin'] = dtx.loc[mask, x_i].astype(str)
        dtx = dtx[['xi_bin']].rename(columns={'xi_bin':x_i})
    ## to charcarter, na to missing
    if not is_string_dtype(dtx[x_i]):
        dtx.loc[:,x_i] = dtx.loc[:,x_i].astype(str).replace('nan', 'missing')
    # dtx.loc[:,x_i] = np.where(pd.isnull(dtx[x_i]), dtx[x_i], dtx[x_i].astype(str))
    dtx = dtx.replace(np.nan, 'missing').assign(rowid = dtx.index).sort_values('rowid')
    # rename binx
    binx.columns = ['bin', x_i, '_'.join([x_i,woe_points])]
    # merge
    dtx_suffix = pd.merge(dtx, binx, how='left', on=x_i).sort_values('rowid')\
      .set_index(dtx.index)[['_'.join([x_i,woe_points])]]
    return dtx_suffix