import
pandas as pd
import
numpy as np
from
sklearn.model_selection
import
train_test_split
from
sklearn.preprocessing
import
MinMaxScaler
from
sklearn.feature_selection
import
SelectKBest
from
sklearn
import
svm
from
sklearn.model_selection
import
RandomizedSearchCV,GridSearchCV
import
warnings
warnings.filterwarnings(
'ignore'
)
import
seaborn as sns
import
matplotlib.pyplot as plt
train
=
pd.read_csv(
'C:\\Users\\prana\\Downloads\\smartphone_activity_dataset.csv'
)
train.drop(columns
=
{
'activity'
},inplace
=
True
)
from
sklearn.preprocessing
import
MinMaxScaler
t
=
MinMaxScaler()
train_f
=
t.fit_transform(train)
train_f
=
pd.DataFrame(train_f)
X_train,X_test,y_train,y_test
=
train_test_split(train_f,
target, test_size
=
0.8
, random_state
=
100
)
from
dask_ml.model_selection
import
GridSearchCV as DaskGridSearchCV
start
=
time.time()
parameters
=
{
'C'
: [
0.1
,
1
,
5
,
10
,
15
,
20
,
100
,
500
],
'gamma'
: [
0.5
,
0.80
,
1
,
0.1
],
'kernel'
: [
'rbf'
,
'linear'
,
'sigmoid'
]}
modelsvc
=
SVC()
gscv
=
DaskGridSearchCV(modelsvc, param_grid
=
parameters, cv
=
5
, n_jobs
=
-
1
)
grid_results
=
gscv.fit(X_train, y_train)
end
=
time.time()
print
(
"Time Taken with Dask GridSearchCV:"
, end
-
start)
start
=
time.time()
gscv
=
GridSearchCV(svm.SVC(), {
'C'
: [
0.1
,
1
,
5
,
10
,
15
,
20
,
100
,
500
],
'gamma'
: [
0.5
,
0.80
,
1
,
0.1
],
'kernel'
: [
'rbf'
,
'linear'
,
'sigmoid'
]
},cv
=
5
,return_train_score
=
False
,n_jobs
=
-
1
)
grid_results
=
gscv.fit(X_train, y_train)
end
=
time.time()
print
(
"Time Taken without Dask GridSearchCV:"
, end
-
start)