from IPython.core.display import HTML
styles = open("Style.css").read()
HTML(styles)

import pandas as pd
import numpy as np
import rpy2.robjects as robjects

pi = robjects.r('pi')
pi[0]

%load_ext rmagic

%%R -o error
set.seed(10)
y<-c(1:1000)
x1<-c(1:1000)*runif(1000,min=0,max=2)
x2<-(c(1:1000)*runif(1000,min=0,max=2))^2
x3<-log(c(1:1000)*runif(1000,min=0,max=2))

all_data<-data.frame(y,x1,x2,x3)
positions <- sample(nrow(all_data),size=floor((nrow(all_data)/4)*3))
training<- all_data[positions,]
testing<- all_data[-positions,]

lm_fit<-lm(y~x1+x2+x3,data=training)
print(summary(lm_fit))

predictions<-predict(lm_fit,newdata=testing)
error<-sqrt((sum((testing$y-predictions)^2))/nrow(testing))

print error

%%R -o training,testing
set.seed(10)
y<-c(1:1000)
x1<-c(1:1000)*runif(1000,min=0,max=2)
x2<-(c(1:1000)*runif(1000,min=0,max=2))^2
x3<-log(c(1:1000)*runif(1000,min=0,max=2))

all_data<-data.frame(y,x1,x2,x3)
positions <- sample(nrow(all_data),size=floor((nrow(all_data)/4)*3))
training<- all_data[positions,]
testing<- all_data[-positions,]

tr = pd.DataFrame(dict(zip(['y', 'x1', 'x2', 'x3'], training)))
te = pd.DataFrame(dict(zip(['y', 'x1', 'x2', 'x3'], testing)))

tr.head()

from statsmodels.formula.api import ols

lm = ols('y ~ x1 + x2 + x3', tr).fit()
lm.summary()

pred = lm.predict(te)

error = sqrt((sum((te.y - pred)**2)) / len(te))
error

X = np.array([0,1,2,3,4])
Y = np.array([3,5,4,6,7])

%%R -i X,Y -o XYcoef
XYlm = lm(Y~X)
XYcoef = coef(XYlm)
print(summary(XYlm))
par(mfrow=c(2,2))
plot(XYlm)

XYcoef