コード例 #1
0
def test_cum_count(es):
    log_id_feat = es['log']['id']
    cum_count = CumCount(log_id_feat, es['log']['session_id'])
    features = [cum_count]
    pandas_backend = PandasBackend(es, features)
    df = pandas_backend.calculate_all_features(instance_ids=range(15),
                                               time_last=None)
    cvalues = df[cum_count.get_name()].values
    assert len(cvalues) == 15
    cum_count_values = [1, 2, 3, 4, 5, 1, 2, 3, 4, 1, 1, 2, 1, 2, 3]
    for i, v in enumerate(cum_count_values):
        assert v == cvalues[i]
コード例 #2
0
def test_cum_count(es):
    log_id_feat = es['log']['id']
    cum_count = CumCount(log_id_feat, es['log']['session_id'])
    features = [cum_count]
    pandas_backend = PandasBackend(es, features)
    df = pandas_backend.calculate_all_features(instance_ids=range(15),
                                               time_last=None)
    cvalues = df[cum_count.get_name()].values
    assert len(cvalues) == 15
    cum_count_values = [1, 2, 3, 4, 5, 1, 2, 3, 4, 1, 1, 2, 1, 2, 3]
    for i, v in enumerate(cum_count_values):
        assert v == cvalues[i]
コード例 #3
0
def test_cum_handles_uses_full_entity(es):
    def check(feature):
        pandas_backend = PandasBackend(es, [feature])
        df_1 = pandas_backend.calculate_all_features(instance_ids=[0, 1, 2],
                                                     time_last=None)
        df_2 = pandas_backend.calculate_all_features(instance_ids=[2],
                                                     time_last=None)

        # check that the value for instance id 2 matches
        assert (df_2.loc[2] == df_1.loc[2]).all()

    for primitive in [CumSum, CumMean, CumMax, CumMin]:
        check(primitive(es['log']['value'], es['log']['session_id']))

    check(CumCount(es['log']['id'], es['log']['session_id']))
コード例 #4
0
    verbose = 1,
	target_entity='WIP',
    agg_primitives=[], 
	trans_primitives=['cum_sum', 'cum_count'], 
	groupby_trans_primitives=['cum_sum', 'cum_count'], #累積總計、累積總數
    
    ignore_variables={'WIP': ['PRIORITY']}
    
	)
feature_matrix    


# %%
from featuretools.primitives import CumCount
#累績總數
cum_count = CumCount()
cum_count([1, 2, 3, 4, None, 5]).tolist()


# %%
from featuretools.primitives import CumCount
from featuretools.primitives import IsWeekend
#累績總數
cum_count = CumCount()
cum_count([1, 2, 3, 4, None, 5]).tolist()
isWkend = IsWeekend()
feature_matrix, features_list = ft.dfs(entityset=es, 
    verbose = 1,
	target_entity='WIP',
    agg_primitives=[], 
	trans_primitives=['cum_sum','cum_count','is_weekend'],