10 examples of 'pandas fillna with another column' in Python

114
def panel_fillna(panel, type="bfill"):
115
    """
116
    fill nan along the 3rd axis
117
    :param panel: the panel to be filled
118
    :param type: bfill or ffill
119
    """
120
    frames = {}
121
    for item in panel.items:
122
        if type == "both":
123
            frames[item] = panel.loc[item].fillna(axis=1, method="bfill").\
124
                fillna(axis=1, method="ffill")
125
        else:
126
            frames[item] = panel.loc[item].fillna(axis=1, method=type)
127
    return pd.Panel(frames)

19
def fill_missing_values(df_data):
20
    """Fill missing values in data frame, in place."""    
21
    df_data.fillna(method="ffill", inplace="True")
22
    df_data.fillna(method='bfill', inplace="True")

39
def _drop_col(self, df):
40
    '''
41
    Drops last column, which was added in the parsing procedure due to a
42
    trailing white space for each sample in the text file
43
    Arguments:
44
        df: pandas dataframe
45
    Return:
46
        df: original df with last column dropped
47
    '''
48
    return df.drop(df.columns[-1], axis=1)

3169
def hpat_pandas_series_dropna_impl(self, axis=0, inplace=False):
3170
    # generate Series index if needed by using SeriesType.index (i.e. not self._index)
3171
    na_data_arr = hpat.hiframes.api.get_nan_mask(self._data)
3172
    data = self._data[~na_data_arr]
3173
    index = self.index[~na_data_arr]
3174
    return pandas.Series(data, index, self._name)

2413
def combine_first(self, other):
2414
    """Combine two Datasets, default to data_vars of self.
2415
2416
    The new coordinates follow the normal broadcasting and alignment rules
2417
    of ``join='outer'``.  Vacant cells in the expanded coordinates are
2418
    filled with np.nan.
2419
2420
    Parameters
2421
    ----------
2422
    other : DataArray
2423
        Used to fill all matching missing values in this array.
2424
2425
    Returns
2426
    -------
2427
    DataArray
2428
    """
2429
    out = ops.fillna(self, other, join="outer", dataset_join="outer")
2430
    return out

38
def fill_empty(df: pd.DataFrame) -> pd.DataFrame:
39
    """Fill the gaps in the 'original' column with values from 'index'
40
    Args:
41
        df:
42
    Returns:
43
    """
44
    index = df["original"].isnull()
45
    df.loc[index, "original"] = df.loc[index, "index"]
46
47
    return df

580
def sdc_fillna_int_impl(self, inplace=False, value=None):
581
    return copy(self)

332
def dropcols(df, start=None, end=None):
333
    """Drop columns that contain NaN within [start, end] inclusive.
334
335
    A wrapper around DataFrame.dropna() that builds an easier *subset*
336
    syntax for tseries-indexed DataFrames.
337
338
    Parameters
339
    ----------
340
    df : DataFrame
341
    start : str or datetime, default None
342
        start cutoff date, inclusive
343
    end : str or datetime, default None
344
        end cutoff date, inclusive
345
346
    Example
347
    -------
348
    df = DataFrame(np.random.randn(10,3),
349
                   index=pd.date_range('2017', periods=10))
350
351
    # Drop in some NaN
352
    df.set_value('2017-01-04', 0, np.nan)
353
    df.set_value('2017-01-02', 2, np.nan)
354
    df.loc['2017-01-05':, 1] = np.nan
355
356
    # only col2 will be kept--its NaN value falls before `start`
357
    print(dropcols(df, start='2017-01-03'))
358
                      2
359
    2017-01-01  0.12939
360
    2017-01-02      NaN
361
    2017-01-03  0.16596
362
    2017-01-04  1.06442
363
    2017-01-05 -1.87040
364
    2017-01-06 -0.17160
365
    2017-01-07  0.94588
366
    2017-01-08  1.49246
367
    2017-01-09  0.02042
368
    2017-01-10  0.75094
369
370
    """
371
372
    if isinstance(df, Series):
373
        raise ValueError("func only applies to `pd.DataFrame`")
374
    if start is None:
375
        start = df.index[0]
376
    if end is None:
377
        end = df.index[-1]
378
    subset = df.index[(df.index >= start) & (df.index <= end)]
379
    return df.dropna(axis=1, subset=subset)

29
def _concat(df, type):
30
    if df is None:
31
        df = pd.DataFrame(_object_blocks[type])
32
    else:
33
        _df = pd.DataFrame(_object_blocks[type])
34
        df = pd.concat([df, _df], sort=True)
35
    return df

813
def merge(old_cols, new_cols):
814
    return old_cols + new_cols