def test_convert_to_output_format_ok(self, input, expected_output):
actual_output = to_output(input)
assert expected_output == actual_output
try:
json.dumps(actual_output)
except Exception:
raise AssertionError("Could not dump result into json")
def predict(self, instance):
"""
instance:
Since we're doing scheduled prediction, this will be a data spec
describing the data we should do prediction on.
Note that it's also possible to take api_key and project in as
optional arguments here.
"""
dts = DataFetcher(instance)
df = dts.time_series.fetch_dataframe(["temp", "pressure", "rpm"]).dropna()
X = df[["temp", "pressure", "rpm"]].values
df["production_rate"] = self.regressor.predict(X)
# For scheduled prediction we need to return output on the format:
# {
# "timeSeries":
# { "production_rate": [(t0, p0), (t1, p1), (t2, p2), ...] }
# }
# We can use a model hosting utilities method to convert our dataframe
# to this format.
return to_output(df[["timestamp", "production_rate"]])
def predict(self, instance):
data_fetcher = DataFetcher(instance,
client_name="simple-transform-client")
df = data_fetcher.time_series.fetch_dataframe(["x1", "x2"])
df["y"] = (df["x1"] + df["x2"]) / math.pi
return to_output(df[["y"]])
def predict(self, instance):
data_fetcher = DataFetcher(instance)
df = data_fetcher.time_series.fetch_dataframe(["x1", "x2"])
df["y"] = (df["x1"] + df["x2"]) / math.pi
return to_output(df[["y", "timestamp"]])
def test_convert_to_output_duplicate_alias(self):
with pytest.raises(DuplicateAliasInScheduledOutput, match="multiple"):
to_output([
pd.DataFrame({"x": [1]}, index=[1]),
pd.DataFrame({"x": [1]}, index=[1])
])
def predict(self, instance):
data_fetcher = DataFetcher(instance)
df = data_fetcher.time_series.fetch_dataframe(["x1", "x2"])
df["y"] = df["x2"] / df["x1"]
return to_output(df.size)
def predict(self, instance):
data_fetcher = DataFetcher(instance, client_name="cprfix-client")
df = data_fetcher.time_series.fetch_dataframe(["x1", "x2"])
df["y"] = df["x2"] / df["x1"]
return to_output(df[["y"]])