def create_data(
X: dt.Frame = None
) -> Union[str, List[str], dt.Frame, List[dt.Frame], np.ndarray,
List[np.ndarray], pd.DataFrame, List[pd.DataFrame], Dict[
str, str], # {data set names : paths}
Dict[str, dt.Frame], # {data set names : dt frames}
Dict[str, np.ndarray], # {data set names : np arrays}
Dict[str, pd.DataFrame], # {data set names : pd frames}
]:
col_count = 2
col_names = ["random_col_1", "random_col_2"]
if col_count != len(col_names):
raise ValueError(
"Number of column names must be equal to number of columns.")
if X is None:
return []
rcol = dt.Frame(np.random.randint(0, 100,
size=(X.shape[0], col_count)))
rcol.names = col_names
X.cbind(rcol)
return X
def transform(self, X: dt.Frame):
def get_ua_info(ua_string):
from user_agents import parse
ua = parse(ua_string)
return ua.browser.family, ua.os.family, ua.device.family, ua.is_mobile, ua.is_tablet
ua_column_names = ['ua', 'user-agent', 'user_agent', 'useragent']
col_name = X.names[0]
if col_name in ua_column_names:
newnames = ("browser", "os", "device", "is_mobile", "is_tablet")
Y = X[col_name].to_list()[0]
Z = dt.Frame([get_ua_info(x) for x in Y],
names=[f"{col_name}_{s}" for s in newnames])
X.cbind(Z)
return X
else:
return X.to_pandas().iloc[:, 0]
def create_data(X: dt.Frame = None) -> Union[
str, List[str],
dt.Frame, List[dt.Frame],
np.ndarray, List[np.ndarray],
pd.DataFrame, List[pd.DataFrame],
Dict[str, str], # {data set names : paths}
Dict[str, dt.Frame], # {data set names : dt frames}
Dict[str, np.ndarray], # {data set names : np arrays}
Dict[str, pd.DataFrame], # {data set names : pd frames}
]:
pytrends = TrendReq(hl='en-US', tz=360)
kw_list = ["sanitizing wipes"]
geo = ["US-TX", "US-CA", "US-NY"]
geo = "US-TX"
timeframe = '2020-01-01 2020-05-08'
timeframe = 'today 5-y'
pytrends.build_payload(kw_list, timeframe=timeframe, geo=geo)
trends = pytrends.interest_over_time()
X = dt.Frame(date = trends.index.to_list())
X.cbind(dt.Frame(gtrend = trends.iloc[:, 0].tolist(), isPartial = trends.iloc[:, 1].tolist()))
return {"gtrends_sanitizing_wipes":X[dt.f.isPartial == 'False', :]}
