def train_and_persist(model_dir=None, hour_path=None, model="xgboost"):
valid = {"xgboost", "ridge"}
if model not in valid:
raise ValueError("results: model must be one of %s." % valid)
else:
hour = read_data(hour_path)
hour = preprocess(hour)
hour = dummify(hour)
hour = postprocess(hour)
if model == "xgboost":
model_result = train_xgboost(hour)
else:
model_result = train_ridge(hour)
model_path = get_model_path(model, model_dir)
joblib.dump(model_result, model_path)
def train_and_persist(model_dir=None, hour_path=None, model="xgboost"):
hour = read_data(hour_path)
hour = preprocess(hour)
hour = dummify(hour)
hour = postprocess(hour)
model_path = get_model_path(model_dir, model)
# Implement other models?
if model == "ridge":
model_object, score_train = train_ridge(hour)
else:
model_object, score_train = train_xgboost(hour)
joblib.dump(model_object, model_path)
return score_train
def train_and_persist(model_dir=None, hour_path=None, model_name="xgboost"):
hour = read_data(hour_path)
hour = preprocess(hour)
hour = dummify(hour)
hour = postprocess(hour)
##added
# TODO: Implement other models?
if model_name == "xgboost":
model = train_xgboost(hour)
elif model_name == "ridge":
model = train_ridge(hour)
elif model_name == "lasso":
model = train_lasso(hour)
else:
print("model should be equal to 'xgboost' or 'ridge' or 'lasso'")
model_path = get_model_path(model_dir, model_name)
joblib.dump(model, model_path)
def get_predict():
# Input means
df = read_data()
weather_avg = df['weathersit'].mean()
temp_avg = df['temp'].mean()
feeling_avg = df['atemp'].mean()
humidity_avg = df["hum"].mean()
windspeed_avg = df["windspeed"].mean()
parameters = dict(request.args)
parameters["date"] = dt.datetime.fromisoformat(parameters["date"])
parameters["weathersit"] = int(parameters.get("weathersit", weather_avg))
parameters["temperature_C"] = float(
parameters.get("temperature_C", temp_avg))
parameters["feeling_temperature_C"] = float(
parameters.get("feeling_temperature_C", feeling_avg))
parameters["humidity"] = float(parameters.get("humidity", humidity_avg))
parameters["windspeed"] = float(parameters.get("windspeed", windspeed_avg))
#parameters["weathersit"] = int(parameters["weathersit"])
#parameters["date"] = dt.datetime.fromisoformat(parameters["date"])
#parameters["temperature_C"] = float(parameters["temperature_C"])
#parameters["feeling_temperature_C"] = float(parameters["feeling_temperature_C"])
#parameters["humidity"] = float(parameters["humidity"])
#parameters["windspeed"] = float(parameters["windspeed"])
model = str(parameters["model"])
start_prediction = dt.datetime.now()
result = predict(parameters, model=model)
#parameters.get('model'))
end_prediction = dt.datetime.now() - start_prediction
return {
"result": result,
"computation time": end_prediction.total_seconds()
}
def get_input_dict(parameters):
hour_original = read_data()
base_year = pd.to_datetime(hour_original["dteday"]).min().year
date = parameters["date"]
is_holiday = date in US_HOLIDAYS
is_weekend = date.weekday() in (5, 6)
row = pd.Series(
{
"dteday": date.strftime("%Y-%m-%d"),
"season": get_season(date),
"yr": date.year - base_year,
"mnth": date.month,
"hr": date.hour,
"holiday": 1 if is_holiday else 0,
"weekday": (date.weekday() + 1) % 7,
"workingday": 0 if is_holiday or is_weekend else 1,
"weathersit": parameters["weathersit"],
"temp": parameters["temperature_C"] / 41.0,
"atemp": parameters["feeling_temperature_C"] / 50.0,
"hum": parameters["humidity"] / 100.0,
"windspeed": parameters["windspeed"] / 67.0,
"cnt": 1, # Dummy, unused for prediction
}
)
dummified_original = dummify(preprocess(hour_original))
df = pd.DataFrame([row])
df = preprocess(df)
df = dummify(df, dummified_original.columns)
df = postprocess(df)
df = df.drop(columns=["dteday", "atemp", "casual", "registered", "cnt"])
assert len(df) == 1
return df.iloc[0].to_dict()
def get_predict():
tomorrow = dt.datetime.now() + dt.timedelta(days=1)
hour_original = read_data()
hour_original = hour_original[hour_original.mnth == tomorrow.month]
weathersit_avg = hour_original["weathersit"].median()
temperature_C_avg = hour_original.temp.mean() * 41.0
feeling_temperature_C_avg = hour_original.atemp.mean() * 50.0
humiditiy_avg = hour_original.hum.mean() * 100.0
windspeed_avg = hour_original.windspeed.mean() * 67.0
parameters = dict(request.args)
parameters["date"] = dt.datetime.fromisoformat(
parameters.get("date", tomorrow.isoformat()))
parameters["weathersit"] = int(parameters.get("weathersit",
weathersit_avg))
parameters["temperature_C"] = float(
parameters.get("temperature_C", temperature_C_avg))
parameters["feeling_temperature_C"] = float(
parameters.get("feeling_temperature_C", feeling_temperature_C_avg))
parameters["humidity"] = float(parameters.get("humidity", humiditiy_avg))
parameters["windspeed"] = float(parameters.get("windspeed", windspeed_avg))
start = dt.datetime.now()
result = predict(parameters, model=parameters.get("model", "xgboost"))
prediction_time = dt.datetime.now() - start
return {
"result": result,
"prediction time (seconds)": prediction_time.total_seconds(),
"date": parameters["date"],
}
