def test_accepts_cutoff_time_compose(dataframes, relationships):
def fraud_occured(df):
return df["fraud"].any()
lm = cp.LabelMaker(
target_dataframe_name="card_id",
time_index="transaction_time",
labeling_function=fraud_occured,
window_size=1,
)
transactions_df = to_pandas(dataframes["transactions"][0])
labels = lm.search(transactions_df, num_examples_per_instance=-1)
labels["time"] = pd.to_numeric(labels["time"])
labels.rename({"card_id": "id"}, axis=1, inplace=True)
feature_matrix, features = dfs(
dataframes=dataframes,
relationships=relationships,
target_dataframe_name="cards",
cutoff_time=labels,
)
feature_matrix = to_pandas(feature_matrix, index="id")
assert len(feature_matrix.index) == 6
assert len(feature_matrix.columns) == len(features) + 1
def test_accepts_cutoff_time_compose(entities, relationships):
def fraud_occured(df):
return df['fraud'].any()
lm = cp.LabelMaker(target_entity='card_id',
time_index='transaction_time',
labeling_function=fraud_occured,
window_size=1)
transactions_df = entities['transactions'][0]
if isinstance(transactions_df, dd.DataFrame):
transactions_df = transactions_df.compute()
labels = lm.search(transactions_df, num_examples_per_instance=-1)
labels['time'] = pd.to_numeric(labels['time'])
labels.rename({'card_id': 'id'}, axis=1, inplace=True)
feature_matrix, features = dfs(entities=entities,
relationships=relationships,
target_entity="cards",
cutoff_time=labels)
if isinstance(feature_matrix, dd.DataFrame):
feature_matrix = feature_matrix.compute().set_index('id')
assert len(feature_matrix.index) == 6
assert len(feature_matrix.columns) == len(features) + 1
def lt(es):
def label_func(df):
return df['value'].sum() > 10
lm = cp.LabelMaker(target_entity='id',
time_index='datetime',
labeling_function=label_func,
window_size='1m')
df = es['log'].df
df = to_pandas(df)
labels = lm.search(df, num_examples_per_instance=-1)
labels = labels.rename(columns={'cutoff_time': 'time'})
return labels
def lt(es):
def label_func(df):
return df["value"].sum() > 10
lm = cp.LabelMaker(
target_dataframe_name="id",
time_index="datetime",
labeling_function=label_func,
window_size="1m",
)
df = es["log"]
df = to_pandas(df)
labels = lm.search(df, num_examples_per_instance=-1)
labels = labels.rename(columns={"cutoff_time": "time"})
return labels
def total_spent(transactions, total_spent_fn):
lm = cp.LabelMaker(target_entity='customer_id',
time_index='time',
labeling_function=total_spent_fn)
lt = lm.search(transactions, num_examples_per_instance=1, verbose=False)
return lt