Python pandas.notna方法代码示例

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def _similarity_smooth(presented, recalled, features, distance):
    lists = presented.index.get_values()
    res = np.empty((len(lists), len(features), recalled.iloc[0].shape[0], presented.iloc[0].shape[0]))*np.nan
    for li, l in enumerate(lists):
        p_list = presented.loc[l]
        r_list = recalled.loc[l]
        for i, feature in enumerate(features):
            get_feature = lambda x: np.array(x[feature]) if np.array(pd.notna(x['item'])).any() else np.nan
            p = np.vstack(p_list.apply(get_feature).get_values())
            r = r_list.dropna().apply(get_feature).get_values()
            r = np.vstack(list(filter(lambda x: x is not np.nan, r)))
            tmp = 1 - cdist(r, p, distance)
            res[li, i, :tmp.shape[0], :] =  tmp
    if distance == 'correlation':
        return np.nanmean(res, 1)
    else:
        return np.mean(res, 1) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_where_other(self):
        # other is ndarray or Index
        i = pd.date_range('20130101', periods=3, tz='US/Eastern')

        for arr in [np.nan, pd.NaT]:
            result = i.where(notna(i), other=np.nan)
            expected = i
            tm.assert_index_equal(result, expected)

        i2 = i.copy()
        i2 = Index([pd.NaT, pd.NaT] + i[2:].tolist())
        result = i.where(notna(i2), i2)
        tm.assert_index_equal(result, i2)

        i2 = i.copy()
        i2 = Index([pd.NaT, pd.NaT] + i[2:].tolist())
        result = i.where(notna(i2), i2.values)
        tm.assert_index_equal(result, i2) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_basic(self):

        # array or list or dates
        N = 50
        rng = date_range('1/1/1990', periods=N, freq='53s')
        ts = Series(np.random.randn(N), index=rng)
        ts[15:30] = np.nan
        dates = date_range('1/1/1990', periods=N * 3, freq='25s')

        result = ts.asof(dates)
        assert notna(result).all()
        lb = ts.index[14]
        ub = ts.index[30]

        result = ts.asof(list(dates))
        assert notna(result).all()
        lb = ts.index[14]
        ub = ts.index[30]

        mask = (result.index >= lb) & (result.index < ub)
        rs = result[mask]
        assert (rs == ts[lb]).all()

        val = result[result.index[result.index >= ub][0]]
        assert ts[ub] == val 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_len(self):
        values = Series(['foo', 'fooo', 'fooooo', np.nan, 'fooooooo'])

        result = values.str.len()
        exp = values.map(lambda x: len(x) if notna(x) else NA)
        tm.assert_series_equal(result, exp)

        # mixed
        mixed = Series(['a_b', NA, 'asdf_cas_asdf', True, datetime.today(),
                        'foo', None, 1, 2.])

        rs = Series(mixed).str.len()
        xp = Series([3, NA, 13, NA, NA, 3, NA, NA, NA])

        assert isinstance(rs, Series)
        tm.assert_almost_equal(rs, xp)

        # unicode
        values = Series([u('foo'), u('fooo'), u('fooooo'), np.nan, u(
            'fooooooo')])

        result = values.str.len()
        exp = values.map(lambda x: len(x) if notna(x) else NA)
        tm.assert_series_equal(result, exp) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_setitem(self):

        df = self.df
        idx = self.idx

        # setitem
        df['C'] = idx
        assert_series_equal(df['C'], Series(idx, name='C'))

        df['D'] = 'foo'
        df['D'] = idx
        assert_series_equal(df['D'], Series(idx, name='D'))
        del df['D']

        # With NaN: because uint64 has no NaN element,
        # the column should be cast to object.
        df2 = df.copy()
        df2.iloc[1, 1] = pd.NaT
        df2.iloc[1, 2] = pd.NaT
        result = df2['B']
        assert_series_equal(notna(result), Series(
            [True, False, True], name='B'))
        assert_series_equal(df2.dtypes, Series([np.dtype('uint64'),
                                                np.dtype('O'), np.dtype('O')],
                                               index=['A', 'B', 'C'])) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def kdata_df_save(df, to_path, calculate_change=False):
    df = df.drop_duplicates(subset='timestamp', keep='last')
    df = df.set_index(df['timestamp'], drop=False)
    df.index = pd.to_datetime(df.index)
    df = df.sort_index()

    if calculate_change:
        pre_close = None
        for index in df.index:
            try:
                if pd.notna(df.loc[index, ['preClose', 'change', 'changePct']]).all():
                    continue
                current_close = df.loc[index, 'close']
                if pre_close:
                    df.loc[index, 'preClose'] = pre_close
                    change = current_close - pre_close
                    df.loc[index, 'change'] = change
                    df.loc[index, 'changePct'] = change / current_close
                pre_close = df.loc[index, 'close']
            except  Exception as e:
                logger.exception("pre_close:{},current:{}".format(pre_close, df.loc[index, :].to_dict()), e)

    df.to_csv(to_path, index=False) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def earliest(s):
    """
    Finds the earliest date from the columns of an activity dataframe that show messages sent per date.

    Takes a pandas.Series where the columns are the dates (and a couple of calculated columns which will be ignored for the purposes of the calculation) and the cells are the number of messages sent on each date.
    """
    just_dates = s.drop(['Earliest Date', 'Latest Date', 'Total Messages', 'Tenure'], errors='ignore')
    
    earliest = None

    if 'Earliest Date' in s.index:
        if pd.notna(s['Earliest Date']):
            earliest = s['Earliest Date']
    
    # limited to all the dates where the value is greater than 0
    # then take the array of the dates and calculate the min value
    earliest_date = just_dates.loc[just_dates > 0].index.min()

    if earliest is not None:
        if earliest < earliest_date:
            return earliest
    return earliest_date 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def latest(s):
    """
    Finds the latest date from the columns of an activity dataframe that show messages sent per date.

    Takes a pandas.Series where the columns are the dates (and a couple of calculated columns which will be ignored for the purposes of the calculation) and the cells are the number of messages sent on each date.
    """
    just_dates = s.drop(['Earliest Date', 'Latest Date', 'Total Messages', 'Tenure'], errors='ignore')
    
    latest = None

    if 'Latest Date' in s.index:
        if pd.notna(s['Latest Date']):
            latest = s['Latest Date']
    
    # limited to all the dates where the value is greater than 0
    # then take the array of the dates and calculate the max value
    latest_date = just_dates.loc[just_dates > 0].index.max()

    if latest is not None:
        if latest > latest_date:
            return latest
    return latest_date 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_where_other(self):

        # other is ndarray or Index
        i = pd.date_range('20130101', periods=3, tz='US/Eastern')

        for arr in [np.nan, pd.NaT]:
            result = i.where(notna(i), other=np.nan)
            expected = i
            tm.assert_index_equal(result, expected)

        i2 = i.copy()
        i2 = Index([pd.NaT, pd.NaT] + i[2:].tolist())
        result = i.where(notna(i2), i2)
        tm.assert_index_equal(result, i2)

        i2 = i.copy()
        i2 = Index([pd.NaT, pd.NaT] + i[2:].tolist())
        result = i.where(notna(i2), i2.values)
        tm.assert_index_equal(result, i2) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_where_tz(self):
        i = pd.date_range('20130101', periods=3, tz='US/Eastern')
        result = i.where(notna(i))
        expected = i
        tm.assert_index_equal(result, expected)

        i2 = i.copy()
        i2 = Index([pd.NaT, pd.NaT] + i[2:].tolist())
        result = i.where(notna(i2))
        expected = i2
        tm.assert_index_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_valid(self, datetime_series):
        ts = datetime_series.copy()
        ts[::2] = np.NaN

        result = ts.dropna()
        assert len(result) == ts.count()
        tm.assert_series_equal(result, ts[1::2])
        tm.assert_series_equal(result, ts[pd.notna(ts)]) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_notna(self):
        ser = Series([0, 5.4, 3, nan, -0.001])
        expected = Series([True, True, True, False, True])
        tm.assert_series_equal(ser.notna(), expected)

        ser = Series(["hi", "", nan])
        expected = Series([True, True, False])
        tm.assert_series_equal(ser.notna(), expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_setitem_always_copy(self):
        s = self.frame['A'].copy()
        self.frame['E'] = s

        self.frame['E'][5:10] = np.nan
        assert notna(s[5:10]).all() 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_where_align(self):

        def create():
            df = DataFrame(np.random.randn(10, 3))
            df.iloc[3:5, 0] = np.nan
            df.iloc[4:6, 1] = np.nan
            df.iloc[5:8, 2] = np.nan
            return df

        # series
        df = create()
        expected = df.fillna(df.mean())
        result = df.where(pd.notna(df), df.mean(), axis='columns')
        assert_frame_equal(result, expected)

        df.where(pd.notna(df), df.mean(), inplace=True, axis='columns')
        assert_frame_equal(df, expected)

        df = create().fillna(0)
        expected = df.apply(lambda x, y: x.where(x > 0, y), y=df[0])
        result = df.where(df > 0, df[0], axis='index')
        assert_frame_equal(result, expected)
        result = df.where(df > 0, df[0], axis='rows')
        assert_frame_equal(result, expected)

        # frame
        df = create()
        expected = df.fillna(1)
        result = df.where(pd.notna(df), DataFrame(
            1, index=df.index, columns=df.columns))
        assert_frame_equal(result, expected) 

# 需要导入模块: import pandas [as 别名]
# 或者: from pandas import notna [as 别名]
def test_series_setitem(self):
        s = self.ymd['A']

        s[2000, 3] = np.nan
        assert isna(s.values[42:65]).all()
        assert notna(s.values[:42]).all()
        assert notna(s.values[65:]).all()

        s[2000, 3, 10] = np.nan
        assert isna(s[49])