adraguidev

from sklearn.model_selection import train_test_split
from sklearn import  svm
from sklearn.metrics import accuracy_score

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

model = svm.SVC()
model.fit(X_train, y_train)
predictions = model.predict(X_test)

adraguidev

import requests #pip install requests
from bs4 import BeautifulSoup as bs # pip install beautifulsoup4

#Load our first page:
r = request.get("URL")

#Convert to a beautiful soup object
soup = bs(r.content)

#Print our html

adraguidev

#crear un h2oframe desde pandas
df_medicine = h2o.H2OFrame(df)

#Convertir H2Odataframe a un Dataframe de Pandas 
df_python=h2o.h2o.as_list(df_medicine, use_pandas=True)
type(df_python)

#Encoding
from collections import defaultdict
from sklearn import preprocessing 

adraguidev

#importamos las librerrias
from pyclustering.cluster.clarans import clarans;
from pyclustering.utils import timedcall;
import pyreadstat

#cargamos la data
filesav = 'datos/democracias_latam.sav'
df, meta = pyreadstat.read_sav(filesav )

df.head(25)

adraguidev

import pandas as pd
import numpy as np

np.random.seed(123) #generamos semilla

variables = ['X', 'Y', 'Z'] #variables
labels = ['ID_0', 'ID_1', 'ID_2', 'ID_3', 'ID_4'] #valores

X = np.random.random_sample([5, 3])*10 #Le damos valores
df = pd.DataFrame(X, columns=variables, index=labels) #Creamos nuestro dataframe aleatorio