ksdkamesh99

model_torch=convert(model,'pytorch')

ksdkamesh99

# Calculation of time for predicting test data

%%time

#prediction of labels for test data

y_pred=model.predict(np.array(x_test))

#importing metrics from sklearn

ksdkamesh99

model=RandomForestClassifier(n_estimators=300)
model.fit(x_train,y_train)

ksdkamesh99

# load CSV file

data=pd.read_csv('winequality_red.csv')

#plot the Countplot for the column quality

sns.countplot(x='quality',data=data)

# store the quality dataframe

ksdkamesh99

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
import seaborn as sns
from hummingbird.ml import convert
from sklearn.model_selection import train_test_split

ksdkamesh99

!pip install hummingbird-ml

ksdkamesh99

%%time
#opening hdf5 file
df_vaex=vaex.open('dataset.csv.hdf5')
print(df_vaex.head())

ksdkamesh99

%%time
#importing vaex library
import vaex
#converting csv to hdf5 format
df=vaex.from_csv('dataset.csv',convert=True)

ksdkamesh99

pip install vaex

ksdkamesh99

#Converting datatype int64 to int32

dataset=dataset.astype('int32')

#info of dataframe

dataset.info()