def test_lm(fit_intercept):
X, y = make_regression(n_samples=100, n_features=5, chunks=50)
lr = LinearRegression(fit_intercept=fit_intercept)
lr.fit(X, y)
lr.predict(X)
if fit_intercept:
assert lr.intercept_ is not None
)
X_traintrial = de.fit_transform(X_traintrial)
de = DummyEncoder(
["year", "hour", "is_holiday", "weekday", "is_workingday", "weathersit"]
)
X_testtrial = de.fit_transform(X_testtrial)
)
lr = LinearRegression()
lr.fit(X_traintrial.values, y_traintrial.values)
X_testtrial = X_testtrial.drop("season", axis=1)
y_predtrial = lr.predict(X_traintrial.values)
y_predtest = lr.predict(X_testtrial.values)
import dask.array as da
y_predtest.compute()
# random forest
rf = RandomForestRegressor(n_estimators=1000, max_depth=10)
rf.fit(X_traintrial, y_traintrial)
rf_pred = rf.predict(X_testtrial)
'Stay_In_Current_City_Years', 'Marital_Status'
]]
target = df['Purchase']
#creating dummies for the categorical variables
data = dd.get_dummies(categorical_variables.categorize()).compute()
#converting dataframe to array
datanew = data.values
#fit the model
from dask_ml.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(datanew, target)
#preparing the test data
test_categorical = test[[
'Gender', 'Age', 'Occupation', 'City_Category',
'Stay_In_Current_City_Years', 'Marital_Status'
]]
test_dummy = dd.get_dummies(test_categorical.categorize()).compute()
testnew = test_dummy.values
#predict on test and upload
pred = lr.predict(testnew)
#Clustering/K-Means
from dask_ml.cluster import KMeans
model = KMeans()
model.fit(datanew, target)
client
# #### Linear Regression
# In[44]:
from scikitplot.metrics import plot_calibration_curve
from scikitplot.plotters import plot_learning_curve
from scikitplot.estimators import plot_feature_importances
# In[45]:
lr = LinearRegression()
with joblib.parallel_backend('dask'):
lr_model = lr.fit(X_train.values, y_train.values)
y_pred_lr = lr.predict(X_test.values)
# In[46]:
mse(y_test.values, y_pred_lr)
# In[47]:
r2_score(y_test.values.compute(), y_pred_lr.compute())
# ### Non Linear Models
# #### Random Forest Regressor
# In[48]: