Python pandas.util.testing.makeTimeDataFrame() Examples

def test_uquery(self):
        frame = tm.makeTimeDataFrame()
        sql.write_frame(frame, name='test_table', con=self.db)
        stmt = 'INSERT INTO test_table VALUES(2.314, -123.1, 1.234, 2.3)'
        self.assertEqual(sql.uquery(stmt, con=self.db), 1)

        try:
            sys.stdout = StringIO()

            self.assertRaises(sqlite3.OperationalError, sql.tquery,
                              'insert into blah values (1)', con=self.db)

            self.assertRaises(sqlite3.OperationalError, sql.tquery,
                              'insert into blah values (1)', con=self.db,
                              retry=True)
        finally:
            sys.stdout = sys.__stdout__ 

def test_getitem_setitem_non_ix_labels(self):
        df = tm.makeTimeDataFrame()

        start, end = df.index[[5, 10]]

        result = df.loc[start:end]
        result2 = df[start:end]
        expected = df[5:11]
        assert_frame_equal(result, expected)
        assert_frame_equal(result2, expected)

        result = df.copy()
        result.loc[start:end] = 0
        result2 = df.copy()
        result2[start:end] = 0
        expected = df.copy()
        expected[5:11] = 0
        assert_frame_equal(result, expected)
        assert_frame_equal(result2, expected) 

def test_skip_group_keys():

    tsf = tm.makeTimeDataFrame()

    grouped = tsf.groupby(lambda x: x.month, group_keys=False)
    result = grouped.apply(lambda x: x.sort_values(by='A')[:3])

    pieces = [group.sort_values(by='A')[:3] for key, group in grouped]

    expected = pd.concat(pieces)
    assert_frame_equal(result, expected)

    grouped = tsf['A'].groupby(lambda x: x.month, group_keys=False)
    result = grouped.apply(lambda x: x.sort_values()[:3])

    pieces = [group.sort_values()[:3] for key, group in grouped]

    expected = pd.concat(pieces)
    assert_series_equal(result, expected) 

def test_take_invalid_kwargs(self):
        indices = [-3, 2, 0, 1]
        s = tm.makeFloatSeries()
        df = tm.makeTimeDataFrame()

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()

        for obj in (s, df, p):
            msg = r"take\(\) got an unexpected keyword argument 'foo'"
            with pytest.raises(TypeError, match=msg):
                obj.take(indices, foo=2)

            msg = "the 'out' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, out=indices)

            msg = "the 'mode' parameter is not supported"
            with pytest.raises(ValueError, match=msg):
                obj.take(indices, mode='clip') 

def test_numpy_transpose(self):
        msg = "the 'axes' parameter is not supported"

        s = tm.makeFloatSeries()
        tm.assert_series_equal(np.transpose(s), s)

        with pytest.raises(ValueError, match=msg):
            np.transpose(s, axes=1)

        df = tm.makeTimeDataFrame()
        tm.assert_frame_equal(np.transpose(np.transpose(df)), df)

        with pytest.raises(ValueError, match=msg):
            np.transpose(df, axes=1)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            p = tm.makePanel()
            tm.assert_panel_equal(np.transpose(
                np.transpose(p, axes=(2, 0, 1)),
                axes=(1, 2, 0)), p) 

def test_first_subset(self):
        ts = tm.makeTimeDataFrame(freq='12h')
        result = ts.first('10d')
        assert len(result) == 20

        ts = tm.makeTimeDataFrame(freq='D')
        result = ts.first('10d')
        assert len(result) == 10

        result = ts.first('3M')
        expected = ts[:'3/31/2000']
        assert_frame_equal(result, expected)

        result = ts.first('21D')
        expected = ts[:21]
        assert_frame_equal(result, expected)

        result = ts[:0].first('3M')
        assert_frame_equal(result, ts[:0]) 

def test_transpose(self):
        msg = (r"transpose\(\) got multiple values for "
               r"keyword argument 'axes'")
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            # calls implementation in pandas/core/base.py
            tm.assert_series_equal(s.transpose(), s)
        for df in [tm.makeTimeDataFrame()]:
            tm.assert_frame_equal(df.transpose().transpose(), df)

        with catch_warnings(record=True):
            simplefilter("ignore", FutureWarning)
            for p in [tm.makePanel()]:
                tm.assert_panel_equal(p.transpose(2, 0, 1)
                                      .transpose(1, 2, 0), p)
                with pytest.raises(TypeError, match=msg):
                    p.transpose(2, 0, 1, axes=(2, 0, 1)) 

def test_groupby_multiple_key(df):
    df = tm.makeTimeDataFrame()
    grouped = df.groupby([lambda x: x.year, lambda x: x.month,
                          lambda x: x.day])
    agged = grouped.sum()
    assert_almost_equal(df.values, agged.values)

    grouped = df.T.groupby([lambda x: x.year,
                            lambda x: x.month,
                            lambda x: x.day], axis=1)

    agged = grouped.agg(lambda x: x.sum())
    tm.assert_index_equal(agged.index, df.columns)
    assert_almost_equal(df.T.values, agged.values)

    agged = grouped.agg(lambda x: x.sum())
    assert_almost_equal(df.T.values, agged.values) 

def test_resample_frame_basic():
    df = tm.makeTimeDataFrame()

    b = TimeGrouper('M')
    g = df.groupby(b)

    # check all cython functions work
    funcs = ['add', 'mean', 'prod', 'min', 'max', 'var']
    for f in funcs:
        g._cython_agg_general(f)

    result = df.resample('A').mean()
    assert_series_equal(result['A'], df['A'].resample('A').mean())

    result = df.resample('M').mean()
    assert_series_equal(result['A'], df['A'].resample('M').mean())

    df.resample('M', kind='period').mean()
    df.resample('W-WED', kind='period').mean() 

def test_write_row_by_row(self):
        frame = tm.makeTimeDataFrame()
        frame.iloc[0, 0] = np.nan
        drop_sql = "DROP TABLE IF EXISTS test"
        create_sql = sql.get_schema(frame, 'test')
        cur = self.conn.cursor()
        cur.execute(drop_sql)
        cur.execute(create_sql)
        ins = "INSERT INTO test VALUES (%s, %s, %s, %s)"
        for idx, row in frame.iterrows():
            fmt_sql = format_query(ins, *row)
            tquery(fmt_sql, cur=cur)

        self.conn.commit()

        result = sql.read_sql("select * from test", con=self.conn)
        result.index = frame.index
        tm.assert_frame_equal(result, frame, check_less_precise=True) 

def test_schema(self):
        frame = tm.makeTimeDataFrame()
        create_sql = sql.get_schema(frame, 'test')
        lines = create_sql.splitlines()
        for l in lines:
            tokens = l.split(' ')
            if len(tokens) == 2 and tokens[0] == 'A':
                assert tokens[1] == 'DATETIME'

        frame = tm.makeTimeDataFrame()
        drop_sql = "DROP TABLE IF EXISTS test"
        create_sql = sql.get_schema(frame, 'test', keys=['A', 'B'])
        lines = create_sql.splitlines()
        assert 'PRIMARY KEY (`A`, `B`)' in create_sql
        cur = self.conn.cursor()
        cur.execute(drop_sql)
        cur.execute(create_sql) 

def test_resample_frame_basic(self):
        df = tm.makeTimeDataFrame()

        b = TimeGrouper('M')
        g = df.groupby(b)

        # check all cython functions work
        funcs = ['add', 'mean', 'prod', 'min', 'max', 'var']
        for f in funcs:
            g._cython_agg_general(f)

        result = df.resample('A').mean()
        assert_series_equal(result['A'], df['A'].resample('A').mean())

        result = df.resample('M').mean()
        assert_series_equal(result['A'], df['A'].resample('M').mean())

        df.resample('M', kind='period').mean()
        df.resample('W-WED', kind='period').mean() 

def test_slice_locs_with_type_mismatch(self):
        df = tm.makeTimeDataFrame()
        stacked = df.stack()
        idx = stacked.index
        tm.assert_raises_regex(TypeError, '^Level type mismatch',
                               idx.slice_locs, (1, 3))
        tm.assert_raises_regex(TypeError, '^Level type mismatch',
                               idx.slice_locs,
                               df.index[5] + timedelta(
                                   seconds=30), (5, 2))
        df = tm.makeCustomDataframe(5, 5)
        stacked = df.stack()
        idx = stacked.index
        with tm.assert_raises_regex(TypeError, '^Level type mismatch'):
            idx.slice_locs(timedelta(seconds=30))
        # TODO: Try creating a UnicodeDecodeError in exception message
        with tm.assert_raises_regex(TypeError, '^Level type mismatch'):
            idx.slice_locs(df.index[1], (16, "a")) 

def test_transpose(self):
        msg = (r"transpose\(\) got multiple values for "
               r"keyword argument 'axes'")
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            # calls implementation in pandas/core/base.py
            tm.assert_series_equal(s.transpose(), s)
        for df in [tm.makeTimeDataFrame()]:
            tm.assert_frame_equal(df.transpose().transpose(), df)

        with catch_warnings(record=True):
            for p in [tm.makePanel()]:
                tm.assert_panel_equal(p.transpose(2, 0, 1)
                                      .transpose(1, 2, 0), p)
                tm.assert_raises_regex(TypeError, msg, p.transpose,
                                       2, 0, 1, axes=(2, 0, 1)) 

def test_take(self):
        indices = [1, 5, -2, 6, 3, -1]
        for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
                  tm.makeObjectSeries()]:
            out = s.take(indices)
            expected = Series(data=s.values.take(indices),
                              index=s.index.take(indices), dtype=s.dtype)
            tm.assert_series_equal(out, expected)
        for df in [tm.makeTimeDataFrame()]:
            out = df.take(indices)
            expected = DataFrame(data=df.values.take(indices, axis=0),
                                 index=df.index.take(indices),
                                 columns=df.columns)
            tm.assert_frame_equal(out, expected)

        indices = [-3, 2, 0, 1]
        with catch_warnings(record=True):
            for p in [tm.makePanel()]:
                out = p.take(indices)
                expected = Panel(data=p.values.take(indices, axis=0),
                                 items=p.items.take(indices),
                                 major_axis=p.major_axis,
                                 minor_axis=p.minor_axis)
                tm.assert_panel_equal(out, expected) 

def test_take_invalid_kwargs(self):
        indices = [-3, 2, 0, 1]
        s = tm.makeFloatSeries()
        df = tm.makeTimeDataFrame()

        with catch_warnings(record=True):
            p = tm.makePanel()

        for obj in (s, df, p):
            msg = r"take\(\) got an unexpected keyword argument 'foo'"
            tm.assert_raises_regex(TypeError, msg, obj.take,
                                   indices, foo=2)

            msg = "the 'out' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, obj.take,
                                   indices, out=indices)

            msg = "the 'mode' parameter is not supported"
            tm.assert_raises_regex(ValueError, msg, obj.take,
                                   indices, mode='clip') 

def test_groupby_multiple_key(df):
    df = tm.makeTimeDataFrame()
    grouped = df.groupby([lambda x: x.year, lambda x: x.month,
                          lambda x: x.day])
    agged = grouped.sum()
    assert_almost_equal(df.values, agged.values)

    grouped = df.T.groupby([lambda x: x.year,
                            lambda x: x.month,
                            lambda x: x.day], axis=1)

    agged = grouped.agg(lambda x: x.sum())
    tm.assert_index_equal(agged.index, df.columns)
    assert_almost_equal(df.T.values, agged.values)

    agged = grouped.agg(lambda x: x.sum())
    assert_almost_equal(df.T.values, agged.values) 

def test_skip_group_keys():

    tsf = tm.makeTimeDataFrame()

    grouped = tsf.groupby(lambda x: x.month, group_keys=False)
    result = grouped.apply(lambda x: x.sort_values(by='A')[:3])

    pieces = []
    for key, group in grouped:
        pieces.append(group.sort_values(by='A')[:3])

    expected = pd.concat(pieces)
    assert_frame_equal(result, expected)

    grouped = tsf['A'].groupby(lambda x: x.month, group_keys=False)
    result = grouped.apply(lambda x: x.sort_values()[:3])

    pieces = []
    for key, group in grouped:
        pieces.append(group.sort_values()[:3])

    expected = pd.concat(pieces)
    assert_series_equal(result, expected) 

def test_getitem_setitem_non_ix_labels(self):
        df = tm.makeTimeDataFrame()

        start, end = df.index[[5, 10]]

        result = df.loc[start:end]
        result2 = df[start:end]
        expected = df[5:11]
        assert_frame_equal(result, expected)
        assert_frame_equal(result2, expected)

        result = df.copy()
        result.loc[start:end] = 0
        result2 = df.copy()
        result2[start:end] = 0
        expected = df.copy()
        expected[5:11] = 0
        assert_frame_equal(result, expected)
        assert_frame_equal(result2, expected) 

def test_first_subset(self):
        ts = tm.makeTimeDataFrame(freq='12h')
        result = ts.first('10d')
        assert len(result) == 20

        ts = tm.makeTimeDataFrame(freq='D')
        result = ts.first('10d')
        assert len(result) == 10

        result = ts.first('3M')
        expected = ts[:'3/31/2000']
        assert_frame_equal(result, expected)

        result = ts.first('21D')
        expected = ts[:21]
        assert_frame_equal(result, expected)

        result = ts[:0].first('3M')
        assert_frame_equal(result, ts[:0]) 

def test_write_row_by_row(self):

        _skip_if_no_pymysql()
        frame = tm.makeTimeDataFrame()
        frame.iloc[0, 0] = np.nan
        drop_sql = "DROP TABLE IF EXISTS test"
        create_sql = sql.get_schema(frame, 'test')
        cur = self.conn.cursor()
        cur.execute(drop_sql)
        cur.execute(create_sql)
        ins = "INSERT INTO test VALUES (%s, %s, %s, %s)"
        for idx, row in frame.iterrows():
            fmt_sql = format_query(ins, *row)
            tquery(fmt_sql, cur=cur)

        self.conn.commit()

        result = sql.read_sql("select * from test", con=self.conn)
        result.index = frame.index
        tm.assert_frame_equal(result, frame, check_less_precise=True) 

def test_schema(self):
        _skip_if_no_pymysql()
        frame = tm.makeTimeDataFrame()
        create_sql = sql.get_schema(frame, 'test')
        lines = create_sql.splitlines()
        for l in lines:
            tokens = l.split(' ')
            if len(tokens) == 2 and tokens[0] == 'A':
                assert tokens[1] == 'DATETIME'

        frame = tm.makeTimeDataFrame()
        drop_sql = "DROP TABLE IF EXISTS test"
        create_sql = sql.get_schema(frame, 'test', keys=['A', 'B'])
        lines = create_sql.splitlines()
        assert 'PRIMARY KEY (`A`, `B`)' in create_sql
        cur = self.conn.cursor()
        cur.execute(drop_sql)
        cur.execute(create_sql) 

def test_resample_frame_basic(self):
        df = tm.makeTimeDataFrame()

        b = TimeGrouper('M')
        g = df.groupby(b)

        # check all cython functions work
        funcs = ['add', 'mean', 'prod', 'min', 'max', 'var']
        for f in funcs:
            g._cython_agg_general(f)

        result = df.resample('A')
        assert_series_equal(result['A'], df['A'].resample('A'))

        result = df.resample('M')
        assert_series_equal(result['A'], df['A'].resample('M'))

        df.resample('M', kind='period')
        df.resample('W-WED', kind='period') 

def test_f_test(self):
        x = tm.makeTimeDataFrame()
        y = x.pop('A')

        model = ols(y=y, x=x)

        hyp = '1*B+1*C+1*D=0'
        result = model.f_test(hyp)

        hyp = ['1*B=0',
               '1*C=0',
               '1*D=0']
        result = model.f_test(hyp)
        assert_almost_equal(result['f-stat'], model.f_stat['f-stat'])

        self.assertRaises(Exception, model.f_test, '1*A=0') 

def test_r2_no_intercept(self):
        y = tm.makeTimeSeries()
        x = tm.makeTimeDataFrame()

        x_with = x.copy()
        x_with['intercept'] = 1.

        model1 = ols(y=y, x=x)
        model2 = ols(y=y, x=x_with, intercept=False)
        assert_series_equal(model1.beta, model2.beta)

        # TODO: can we infer whether the intercept is there...
        self.assert_(model1.r2 != model2.r2)

        # rolling

        model1 = ols(y=y, x=x, window=20)
        model2 = ols(y=y, x=x_with, window=20, intercept=False)
        assert_frame_equal(model1.beta, model2.beta)
        self.assert_((model1.r2 != model2.r2).all()) 

def test_write_row_by_row(self):
        frame = tm.makeTimeDataFrame()
        frame.ix[0, 0] = np.nan
        create_sql = sql.get_schema(frame, 'test', 'sqlite')
        cur = self.db.cursor()
        cur.execute(create_sql)

        cur = self.db.cursor()

        ins = "INSERT INTO test VALUES (%s, %s, %s, %s)"
        for idx, row in frame.iterrows():
            fmt_sql = format_query(ins, *row)
            sql.tquery(fmt_sql, cur=cur)

        self.db.commit()

        result = sql.read_frame("select * from test", con=self.db)
        result.index = frame.index
        tm.assert_frame_equal(result, frame) 

def test_slice_locs_with_type_mismatch():
    df = tm.makeTimeDataFrame()
    stacked = df.stack()
    idx = stacked.index
    with pytest.raises(TypeError, match='^Level type mismatch'):
        idx.slice_locs((1, 3))
    with pytest.raises(TypeError, match='^Level type mismatch'):
        idx.slice_locs(df.index[5] + timedelta(seconds=30), (5, 2))
    df = tm.makeCustomDataframe(5, 5)
    stacked = df.stack()
    idx = stacked.index
    with pytest.raises(TypeError, match='^Level type mismatch'):
        idx.slice_locs(timedelta(seconds=30))
    # TODO: Try creating a UnicodeDecodeError in exception message
    with pytest.raises(TypeError, match='^Level type mismatch'):
        idx.slice_locs(df.index[1], (16, "a")) 

def setup_method(self, method):

        import matplotlib as mpl
        mpl.rcdefaults()

        self.mpl_ge_2_0_1 = plotting._compat._mpl_ge_2_0_1()
        self.mpl_ge_2_1_0 = plotting._compat._mpl_ge_2_1_0()
        self.mpl_ge_2_2_0 = plotting._compat._mpl_ge_2_2_0()
        self.mpl_ge_2_2_2 = plotting._compat._mpl_ge_2_2_2()
        self.mpl_ge_3_0_0 = plotting._compat._mpl_ge_3_0_0()

        self.bp_n_objects = 7
        self.polycollection_factor = 2
        self.default_figsize = (6.4, 4.8)
        self.default_tick_position = 'left'

        n = 100
        with tm.RNGContext(42):
            gender = np.random.choice(['Male', 'Female'], size=n)
            classroom = np.random.choice(['A', 'B', 'C'], size=n)

            self.hist_df = DataFrame({'gender': gender,
                                      'classroom': classroom,
                                      'height': random.normal(66, 4, size=n),
                                      'weight': random.normal(161, 32, size=n),
                                      'category': random.randint(4, size=n)})

        self.tdf = tm.makeTimeDataFrame()
        self.hexbin_df = DataFrame({"A": np.random.uniform(size=20),
                                    "B": np.random.uniform(size=20),
                                    "C": np.arange(20) + np.random.uniform(
                                        size=20)}) 

def test_numpy_squeeze(self):
        s = tm.makeFloatSeries()
        tm.assert_series_equal(np.squeeze(s), s)

        df = tm.makeTimeDataFrame().reindex(columns=['A'])
        tm.assert_series_equal(np.squeeze(df), df['A']) 

def test_execute(self):
        frame = tm.makeTimeDataFrame()
        create_sql = sql.get_schema(frame, 'test')
        cur = self.conn.cursor()
        cur.execute(create_sql)
        ins = "INSERT INTO test VALUES (?, ?, ?, ?)"

        row = frame.iloc[0]
        sql.execute(ins, self.conn, params=tuple(row))
        self.conn.commit()

        result = sql.read_sql("select * from test", self.conn)
        result.index = frame.index[:1]
        tm.assert_frame_equal(result, frame[:1])