import pandas as pd
import dask.dataframe as dd
from dask_ml.linear_model import LinearRegression

# read csv data and prepare
df = dd.read_csv('./DataSet/ToTrain/*', header=0)

# extract training data
y = df.gender
X = df[['url']]

model = LinearRegression(fit_intercept=True)
model.fit(X, y)

from sklearn.tree import DecisionTreeRegressor
from dask.distributed import Client
import joblib

client = Client(processes=False)
with joblib.parallel_backend('dask'):
    model.fit(X, y)