def test_direct_percentile(es):
v = Feature(es['customers']['age'])
p = Percentile(v)
d = Feature(p, es['sessions'])
pandas_backend = PandasBackend(es, [d])
df = pandas_backend.calculate_all_features([0, 1], None)
cust_vals = es['customers'].df[[v.get_name()]]
cust_vals['percentile'] = cust_vals[v.get_name()].rank(pct=True)
true_p = cust_vals['percentile'].loc[[0, 0]]
for t, a in zip(true_p.values, df[d.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_agg_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
agg = Sum(p, es['sessions'])
pandas_backend = PandasBackend(es, [agg])
df = pandas_backend.calculate_all_features([0, 1], None)
log_vals = es['log'].df[[v.get_name(), 'session_id']]
log_vals['percentile'] = log_vals[v.get_name()].rank(pct=True)
true_p = log_vals.groupby('session_id')['percentile'].sum()[[0, 1]]
for t, a in zip(true_p.values, df[agg.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_direct_percentile(es):
v = Feature(es['customers']['age'])
p = Percentile(v)
d = Feature(p, es['sessions'])
pandas_backend = PandasBackend(es, [d])
df = pandas_backend.calculate_all_features([0, 1], None)
cust_vals = es['customers'].df[[v.get_name()]]
cust_vals['percentile'] = cust_vals[v.get_name()].rank(pct=True)
true_p = cust_vals['percentile'].loc[[0, 0]]
for t, a in zip(true_p.values, df[d.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_agg_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
agg = Sum(p, es['sessions'])
pandas_backend = PandasBackend(es, [agg])
df = pandas_backend.calculate_all_features([0, 1], None)
log_vals = es['log'].df[[v.get_name(), 'session_id']]
log_vals['percentile'] = log_vals[v.get_name()].rank(pct=True)
true_p = log_vals.groupby('session_id')['percentile'].sum()[[0, 1]]
for t, a in zip(true_p.values, df[agg.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_direct_agg_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
agg = Sum(p, es['customers'])
d = Feature(agg, es['sessions'])
pandas_backend = PandasBackend(es, [d])
df = pandas_backend.calculate_all_features([0, 1], None)
log_vals = es['log'].df[[v.get_name(), 'session_id']]
log_vals['percentile'] = log_vals[v.get_name()].rank(pct=True)
log_vals['customer_id'] = [0] * 10 + [1] * 5 + [2] * 2
true_p = log_vals.groupby('customer_id')['percentile'].sum().fillna(0)
true_p = true_p[[0, 0]]
for t, a in zip(true_p.values, df[d.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or round(t, 3) == round(a, 3)
def test_direct_agg_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
agg = Sum(p, es['customers'])
d = Feature(agg, es['sessions'])
pandas_backend = PandasBackend(es, [d])
df = pandas_backend.calculate_all_features([0, 1], None)
log_vals = es['log'].df[[v.get_name(), 'session_id']]
log_vals['percentile'] = log_vals[v.get_name()].rank(pct=True)
log_vals['customer_id'] = [0] * 10 + [1] * 5 + [2] * 2
true_p = log_vals.groupby('customer_id')['percentile'].sum().fillna(0)
true_p = true_p[[0, 0]]
for t, a in zip(true_p.values, df[d.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or round(t, 3) == round(a, 3)
def test_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
pandas_backend = PandasBackend(es, [v, p])
df = pandas_backend.calculate_all_features(range(17), None)
true = df[v.get_name()].rank(pct=True)
for t, a in zip(true.values, df[p.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_isin_feat_other_syntax_int(es):
isin = Feature(es['log']['value']).isin([5, 10])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [False, True, True, False, False, False, False, False]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_other_syntax(es):
isin = Feature(es['log']['product_id']).isin(["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_other_syntax_int(es):
isin = Feature(es['log']['value']).isin([5, 10])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [False, True, True, False, False, False, False, False]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_isin_feat_other_syntax(es):
isin = Feature(es['log']['product_id']).isin(["toothpaste", "coke zero"])
features = [isin]
pandas_backend = PandasBackend(es, features)
df = pandas_backend.calculate_all_features(range(8), None)
true = [True, True, True, False, False, True, True, True]
v = df[isin.get_name()].values.tolist()
assert true == v
def test_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
pandas_backend = PandasBackend(es, [p])
df = pandas_backend.calculate_all_features(range(10, 17), None)
true = es['log'].df[v.get_name()].rank(pct=True)
true = true.loc[range(10, 17)]
for t, a in zip(true.values, df[p.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_dependent_percentile(es):
v = Feature(es['log']['value'])
p = Percentile(v)
p2 = Percentile(p - 1)
pandas_backend = PandasBackend(es, [p, p2])
df = pandas_backend.calculate_all_features(range(10, 17), None)
true = es['log'].df[v.get_name()].rank(pct=True)
true = true.loc[range(10, 17)]
for t, a in zip(true.values, df[p.get_name()].values):
assert (pd.isnull(t) and pd.isnull(a)) or t == a
def test_max_hlevel(es):
kwargs = dict(
target_entity_id='log',
entityset=es,
agg_primitives=[Count, Last],
trans_primitives=[Hour],
max_depth=-1,
)
dfs_h_n1 = DeepFeatureSynthesis(max_hlevel=-1, **kwargs)
dfs_h_0 = DeepFeatureSynthesis(max_hlevel=0, **kwargs)
dfs_h_1 = DeepFeatureSynthesis(max_hlevel=1, **kwargs)
feats_n1 = dfs_h_n1.build_features()
feats_n1 = [f.get_name() for f in feats_n1]
feats_0 = dfs_h_0.build_features()
feats_0 = [f.get_name() for f in feats_0]
feats_1 = dfs_h_1.build_features()
feats_1 = [f.get_name() for f in feats_1]
customer_log = Last(es['log']['value'], es['customers'])
session_log = Last(es['log']['value'], es['sessions'])
log_customer_log = Feature(customer_log, es['log'])
log_session_log = Feature(session_log, es['log'])
assert log_customer_log.get_name() in feats_n1
assert log_session_log.get_name() in feats_n1
assert log_customer_log.get_name() not in feats_1
assert log_session_log.get_name() in feats_1
assert log_customer_log.get_name() not in feats_0
assert log_session_log.get_name() not in feats_0
def test_max_hlevel(es):
kwargs = dict(
target_entity_id='log',
entityset=es,
agg_primitives=[Count, Last],
trans_primitives=[Hour],
max_depth=-1,
)
dfs_h_n1 = DeepFeatureSynthesis(max_hlevel=-1, **kwargs)
dfs_h_0 = DeepFeatureSynthesis(max_hlevel=0, **kwargs)
dfs_h_1 = DeepFeatureSynthesis(max_hlevel=1, **kwargs)
feats_n1 = dfs_h_n1.build_features()
feats_n1 = [f.get_name() for f in feats_n1]
feats_0 = dfs_h_0.build_features()
feats_0 = [f.get_name() for f in feats_0]
feats_1 = dfs_h_1.build_features()
feats_1 = [f.get_name() for f in feats_1]
customer_log = Last(es['log']['value'], es['customers'])
session_log = Last(es['log']['value'], es['sessions'])
log_customer_log = Feature(customer_log, es['log'])
log_session_log = Feature(session_log, es['log'])
assert log_customer_log.get_name() in feats_n1
assert log_session_log.get_name() in feats_n1
assert log_customer_log.get_name() not in feats_1
assert log_session_log.get_name() in feats_1
assert log_customer_log.get_name() not in feats_0
assert log_session_log.get_name() not in feats_0