4 examples of 'pandas drop rows with condition' in Python

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)

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)

259
def drop_some(df_: pd.DataFrame, thresh: int) -> pd.DataFrame:
260
    # thresh is the minimum number of NA, the 1 indicates that columns should be dropped not rows
261
    return df_.dropna(1, thresh=thresh)