10 examples of 'drop first column pandas' in Python

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)

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)

35
@property
36
def drop_columns(self):
37
    drop_col=self.uni_table.query('Iv<%s'%(self._iv_threshold))
38
    return pd.concat([drop_col,self.uni_table[self.uni_table['Iv'].isnull()]])

80
def _clean_columns(df, keep_colnames):
81
    new_colnames = []
82
    for i,colname in enumerate(df.columns):
83
        if colname not in keep_colnames:
84
            new_colnames.append(i)
85
        else:
86
            new_colnames.append(colname)
87
    return new_colnames

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

653
def set_index_post_series(df, index_name, drop, column_dtype):
654
    df2 = df.drop("_partitions", axis=1).set_index("_index", drop=True)
655
    df2.index.name = index_name
656
    df2.columns = df2.columns.astype(column_dtype)
657
    return df2

78
def _clean_column(self, column):
79
    if not isinstance(column, (int, str, unicode)):
80
        raise ValueError('{} is not a valid column'.format(column))
81
    return column in self.df.columns

420
def df_column_types_rename(df):
421
    result = [df[x].dtype.name for x in list(df.columns)]
422
    result[:] = [x if x != 'object' else 'string' for x in result]
423
    result[:] = [x if x != 'int64' else 'integer' for x in result]
424
    result[:] = [x if x != 'float64' else 'double' for x in result]
425
    result[:] = [x if x != 'bool' else 'boolean' for x in result]
426
427
    return result

409
def temp_remove_fields(df, removeFields):
410
411
    tempRemoveFields = list(set(df) & set(removeFields))
412
    tempDf = df[tempRemoveFields]
413
    df = df.drop(columns=tempRemoveFields)
414
415
    return df, tempDf

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)