def zscrp(csvs):
for a in csvs:
a0 = pd.read_csv(a)
robjects.r('''
calc.zpos <- function(x) {
ctrl.avgs <- x %>%
group_by(rep, plt_nm) %>%
filter(condt == "+ctrl") %>%
dplyr::summarise(ctrlmean = mean(area),
ctrlstdev = sd(area))
x.zpos <- left_join(x, ctrl.avgs, by = c("rep", "plt_nm")) %>%
mutate(zpos = (area - ctrlmean)/ctrlstdev) %>%
select(-c(ctrlmean, ctrlstdev))
return(x.zpos)
}
''')
r_f = robjects.globalenv['calc.zpos']
res = r_f(a0)
r.data('res')
pd_df = pandas2ri.ri2py_dataframe(res)
# out = a.split('.csv')
pd_df.to_csv(a, index=False)
def load_data() -> pd.DataFrame:
importr('faraway')
r.data('chredlin');
chredlin = pandas2ri.ri2py(r.chredlin)
chredlin = chredlin.set_index(pandas2ri.ri2py(r.chredlin.rownames))
chredlin['log_income'] = np.log(chredlin['income'])
return chredlin
def load_R_dataset(name, package=None, convert=True):
if package:
importr(package)
r.data(name)
robj = r[name]
if convert:
return _convert_robj(robj)
else:
return robj
def load_data(name, package=None, convert=True):
if package:
pack = importr(package)
r.data(name)
robj = r[name]
if convert:
return convert_robj(robj)
else:
return robj
def transform(df, df_len):
pandas2ri.activate()
r.data('df')
pandas_df = df.head(df_len)
col_name = pandas_df.columns.to_list()
col_name.insert(0, "ID")
Inputid = pandas_df.index
pandas_df.reindex(columns=col_name)
pandas_df["ID"] = Inputid
pandas_df = pandas_df.reindex(columns=col_name)
return pandas_df
def test_nnd_hotdeck_using_rpy2():
if rpy2 is None:
print('rpy2 is absent: skipping test')
return
r.data('iris')
pandas2ri.activate()
# or explcitly do:
# iris = pandas2ri.ri2py(r['iris'])
iris = r['iris']
# lab = list([1:15, 51:65, 101:115)
# recipient data.frame
iris_rec = pd.concat([
iris.loc[1:15],
iris.loc[51:65],
iris.loc[101:115],
])
iris_rec.columns
del iris_rec["Petal.Width"]
# donor data.frame
iris_don = pd.concat([
iris.loc[16:50],
iris.loc[66:100],
iris.loc[116:150],
])
del iris_rec["Petal.Length"]
# Now iris.rec and iris.don have the variables
# "Sepal.Length", "Sepal.Width" and "Species"
# in common.
# "Petal.Length" is available only in iris.rec
# "Petal.Width" is available only in iris.don
# find the closest donors using NND hot deck;
# distances are computed on "Sepal.Length" and "Sepal.Width"
x, y = nnd_hotdeck_using_rpy2(
receiver = iris_rec,
donor = iris_don,
donor_classes = 'Species',
z_variables = "Petal.Width",
matching_variables = ["Sepal.Length", "Sepal.Width"]
)
def test_nnd_hotdeck_using_rpy2():
if rpy2 is None:
print('rpy2 is absent: skipping test')
return
r.data('iris')
pandas2ri.activate()
# or explcitly do:
# iris = pandas2ri.ri2py(r['iris'])
iris = r['iris']
# lab = list([1:15, 51:65, 101:115)
# recipient data.frame
iris_rec = pd.concat([
iris.loc[1:15],
iris.loc[51:65],
iris.loc[101:115],
])
iris_rec.columns
del iris_rec["Petal.Width"]
# donor data.frame
iris_don = pd.concat([
iris.loc[16:50],
iris.loc[66:100],
iris.loc[116:150],
])
del iris_rec["Petal.Length"]
# Now iris.rec and iris.don have the variables
# "Sepal.Length", "Sepal.Width" and "Species"
# in common.
# "Petal.Length" is available only in iris.rec
# "Petal.Width" is available only in iris.don
# find the closest donors using NND hot deck;
# distances are computed on "Sepal.Length" and "Sepal.Width"
x, y = nnd_hotdeck_using_rpy2(
receiver = iris_rec,
donor = iris_don,
donor_classes = 'Species',
z_variables = "Petal.Width",
matching_variables = ["Sepal.Length", "Sepal.Width"]
)
def summr(csv):
nm = os.path.basename(csv).split('.')
drnm = os.path.dirname(csv)
a = pd.read_csv(csv)
robjects.r('''
summr <- function(z) {
foo <- z %>% group_by(rep, plt_nm, condt) %>%
dplyr::summarise(mean_OD = mean(`O.D.`), median_OD = median(`O.D.`), sd_OD = sd(`O.D.`), mean_zneg = mean(zneg), sd_zneg = sd(zneg), mean_zpos = mean(zpos), sd_zpos = sd(zpos))
}
''')
r_summr = robjects.globalenv['summr']
raz = r_summr(a)
r.data('raz')
pd_df = pandas2ri.ri2py_dataframe(raz)
pd_df.to_csv((drnm + '/' + nm[0] + '_sumfile.csv'), index=False)
def summr_ov_cd(csv):
nm = os.path.basename(csv).split('.')
drnm = os.path.dirname(csv)
a = pd.read_csv(csv)
robjects.r('''
summr_rp <- function(z) {
foo <- z %>% group_by(condt) %>%
dplyr::summarise(mean_area = mean(area), median_area = median(area), sd_area = sd(area), mean_zneg = mean(zneg), sd_zneg = sd(zneg), mean_zpos = mean(zpos), sd_zpos = sd(zpos))
}
''')
r_summr_rp = robjects.globalenv['summr_rp']
raz = r_summr_rp(a)
r.data('raz')
pd_df = pandas2ri.ri2py_dataframe(raz)
pd_df.to_csv((drnm + '/' + nm[0] + '_sum_ov_condt.csv'), index=False)
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from rpy2.robjects.packages import importr
from rpy2.robjects import r, pandas2ri
import math
# Importing the dataset
pandas2ri.activate()
utils = importr("utils")
AppliedPredictiveModeling = importr("AppliedPredictiveModeling", data=True)
r.data("segmentationOriginal")
dataset = r["segmentationOriginal"]
dataset = pd.get_dummies(dataset)
X = dataset.iloc[:, 1:-3].values
y = dataset.iloc[:, -1].values
# see the frequency of class
Label = pd.value_counts(y).to_frame().reset_index()
print(Label)
# SVM Models
ModelLinear = SVM(X, y)
ModelLinear.Linearparam()
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 10 12:06:35 2015
@author: Kaddabadda
"""
import pandas as pd
from rpy2.robjects import pandas2ri
pandas2ri.activate()
from rpy2.robjects import r
r.data('prediction')
df_iris = pandas2ri.ri2py(r[prediction])
from rpy2 import robjects
Rdir = "I:/DOCUMENTS/WEGC/02_PhD_research/03_Data/ZAMG/SPARTACUS/TMAX/rda/Tx20130227.rda"
f = r'/Tx20130227.rda'
obj = Rdir + f
m=robjects.r('matrix(1:6, nrow=2, ncol=3)')
m = robjects.reval(obj)
rdf = 'I:/DOCUMENTS/WEGC/02_PhD_research/03_Data/ZAMG/SPARTACUS/TMAX/rda/Tx20130227.rda'
pandas2ri.ri2py(rdf)
"""
#Data sets
from rpy2.robjects import r, pandas2ri
def data1(name):
return pandas2ri.ri2py(r[name])
df = data1('iris')
df.describe()
df = data1('mtcars')
df
df.describe()
df2 = data1('mtcars')
df2.describe()
print(r.data())
df3=pandas2ri.ri2py(r('women'))
df3
#$ pip install pydataset
#then just load up any dataset you wish (currently around 757 datasets available) :
from pydataset import data
titanic = data('titanic')
titanic
from sklearn import datasets
from sklearn import datasets
iris = datasets.load_iris()
def test_reproduction():
if rpy2 is None:
return
# Reproducing examples from StatMatch documenation
# https://cran.r-project.org/web/packages/StatMatch/StatMatch.pdf
r.data('iris')
pandas2ri.activate()
# or explcitly do:
# iris = pandas2ri.ri2py(r['iris'])
iris = r['iris']
# lab = list([1:15, 51:65, 101:115)
# recipient data.frame
iris_rec = pd.concat([
iris.loc[1:15],
iris.loc[51:65],
iris.loc[101:115],
])
iris_rec.columns
del iris_rec["Petal.Width"]
# donor data.frame
iris_don = pd.concat([
iris.loc[16:50],
iris.loc[66:100],
iris.loc[116:150],
])
del iris_rec["Petal.Length"]
# Now iris.rec and iris.don have the variables
# "Sepal.Length", "Sepal.Width" and "Species"
# in common.
# "Petal.Length" is available only in iris.rec
# "Petal.Width" is available only in iris.don
# find the closest donors using NND hot deck;
# distances are computed on "Sepal.Length" and "Sepal.Width"
StatMatch = importr("StatMatch")
out_NND = StatMatch.NND_hotdeck(
data_rec = iris_rec, data_don=iris_don,
match_vars = pd.Series(["Sepal.Length", "Sepal.Width"]),
don_class = "Species"
)
# create synthetic data.set, without the
# duplication of the matching variables
fused_0 = pandas2ri.ri2py(
StatMatch.create_fused(
data_rec = iris_rec,
data_don = iris_don,
mtc_ids = out_NND[0],
z_vars = "Petal.Width"
)
)
# create synthetic data.set, with the "duplication"
# of the matching variables
fused_1 = pandas2ri.ri2py(
StatMatch.create_fused(
data_rec = iris_rec,
data_don = iris_don,
mtc_ids = out_NND[0],
z_vars = "Petal.Width",
dup_x = True,
match_vars = pd.Series(["Sepal.Length", "Sepal.Width"])
)
)
del fused_0, fused_1
def load_data(name, package=None):
if package:
pack = importr(package)
r.data(name)
return convert_robj(r[name])
from rpy2.robjects import r
from rpy2.robjects.packages import importr
vars = importr('vars')
urca = importr('urca')
class RVAR(object):
pass
if __name__ == '__main__':
r.data("Canada")
can = r['Canada']
p1ct = r('p1ct <- VAR(Canada, p=1, type="both")')
coefs = r('coefs <- coef(p1ct)')
ecoef = coefs.rx2('e')
# summary(Canada)
# plot(Canada, nc=2, xlab="")
# adf1 <- summary(ur.df(Canada[, "prod"], type = "trend", lags = 2))
# adf1
# adf2 <- summary(ur.df(diff(Canada[, "prod"]), type = "drift", lags = 1))
# adf2
# VARselect(Canada, lag.max = 8, type = "both")
# %% {"slideshow": {"slide_type": "fragment"}}
from rpy2.robjects import r
x = r('c(1,2,3,4)')
type(x)
# %% {"slideshow": {"slide_type": "fragment"}}
v = r('seq(1:10)')
v
# %% {"slideshow": {"slide_type": "slide"}}
from rpy2.robjects import pandas2ri
pandas2ri.activate()
r.library('missMDA')
r.data('orange')
orange = r('orange')
# %% {"slideshow": {"slide_type": "slide"}}
orange
# %% {"slideshow": {"slide_type": "slide"}, "language": "R"}
# library('missMDA')
# data(orange)
# estim_ncpPCA(orange)
# %% {"slideshow": {"slide_type": "fragment"}}
from rpy2.robjects.packages import importr
miss_mda = importr('missMDA')
res = miss_mda.imputePCA(orange,ncp=2)
from numpy import *
import scipy as sp
from pandas import *
from rpy2.robjects.packages import importr
import rpy2.robjects as ro
import rpy2
from rpy2.robjects import pandas2ri
pandas2ri.activate()
ro.r('x=c()')
ro.r('x[1]=22')
ro.r('x[2]=44')
print(ro.r('x'))
# mtcars
ro.r('data(mtcars)')
from rpy2.robjects import r
r.data('mtcars')
print(r['mtcars'].head())
# let's do an lm on mtcars
ro.r('''fit=lm(mpg ~ wt + cyl, data=mtcars)''')
print(ro.r('summary(fit)'))
def load_data() -> pd.DataFrame:
importr('lasso2')
r.data('Prostate')
prostate = pandas2ri.ri2py(r.Prostate)
return prostate
from rpy2.robjects import r
from rpy2.robjects.packages import importr
vars = importr('vars')
urca = importr('urca')
class RVAR(object):
pass
if __name__ == '__main__':
r.data("Canada")
can = r['Canada']
p1ct = r('p1ct <- VAR(Canada, p=1, type="both")')
coefs = r('coefs <- coef(p1ct)')
ecoef = coefs.rx2('e')
# summary(Canada)
# plot(Canada, nc=2, xlab="")
# adf1 <- summary(ur.df(Canada[, "prod"], type = "trend", lags = 2))
# adf1
# adf2 <- summary(ur.df(diff(Canada[, "prod"]), type = "drift", lags = 1))
# adf2
# VARselect(Canada, lag.max = 8, type = "both")
# Canada <- Canada[, c("prod", "e", "U", "rw")]
def test_reproduction():
if rpy2 is None:
return
# Reproducing examples from StatMatch documenation
# https://cran.r-project.org/web/packages/StatMatch/StatMatch.pdf
r.data('iris')
pandas2ri.activate()
# or explcitly do:
# iris = pandas2ri.ri2py(r['iris'])
iris = r['iris']
# lab = list([1:15, 51:65, 101:115)
# recipient data.frame
iris_rec = pd.concat([
iris.loc[1:15],
iris.loc[51:65],
iris.loc[101:115],
])
iris_rec.columns
del iris_rec["Petal.Width"]
# donor data.frame
iris_don = pd.concat([
iris.loc[16:50],
iris.loc[66:100],
iris.loc[116:150],
])
del iris_rec["Petal.Length"]
# Now iris.rec and iris.don have the variables
# "Sepal.Length", "Sepal.Width" and "Species"
# in common.
# "Petal.Length" is available only in iris.rec
# "Petal.Width" is available only in iris.don
# find the closest donors using NND hot deck;
# distances are computed on "Sepal.Length" and "Sepal.Width"
StatMatch = importr("StatMatch")
out_NND = StatMatch.NND_hotdeck(
data_rec = iris_rec, data_don=iris_don,
match_vars = pd.Series(["Sepal.Length", "Sepal.Width"]),
don_class = "Species"
)
# create synthetic data.set, without the
# duplication of the matching variables
fused_0 = pandas2ri.ri2py(
StatMatch.create_fused(
data_rec = iris_rec,
data_don = iris_don,
mtc_ids = out_NND[0],
z_vars = "Petal.Width"
)
)
# create synthetic data.set, with the "duplication"
# of the matching variables
fused_1 = pandas2ri.ri2py(
StatMatch.create_fused(
data_rec = iris_rec,
data_don = iris_don,
mtc_ids = out_NND[0],
z_vars = "Petal.Width",
dup_x = True,
match_vars = pd.Series(["Sepal.Length", "Sepal.Width"])
)
)
del fused_0, fused_1
# -*- coding: utf-8 -*-
"""
Created on Thu Sep 6 12:18:34 2018
@author: LatizeExpress
"""
import pandas as pd
import numpy
import matplotlib
import matplotlib.pyplot as plt
import rpy2.robjects as robjects
from rpy2.robjects import r, pandas2ri
pandas2ri.activate()
path = "E:/Working/INNERJOIN_WORKING/RefinedData_groupby5.rds"
#path ="D:/NTUC/raw_data/rds_source/TransactionalData/customer1.rds"
r.data(path)
readRDS = robjects.r['readRDS']
df = readRDS(path)
df = pandas2ri.ri2py(df)
# Writing ot csv f
df.to_csv("income_groupby1.csv", index=False, encoding='utf8')
rplot = robjects.r['plot']
grdevices = importr('grDevices')
result = rmcreg(x, y, method_reg="Deming", alpha=0.05)
grdevices.png(file="MethodComparison.png", width=512, height=512)
p = rplot(result)
grdevices.dev_off()
data = load_iris()
df = pd.DataFrame(data.data, columns=data.feature_names)
#print(df.head())
r.data('iris')
pandas2ri.activate()
#r_dataframe = pandas2ri.py2ri(df)
grdevices = importr('grDevices')
result2 = rmcreg(r['iris']["Petal.Length"],
r['iris']["Petal.Width"],
method_reg="PaBa",
alpha=0.05)
grdevices.png(file="iris.png", width=512, height=512)
p = rplot(result2, identity=False)
grdevices.dev_off()
print(r['iris']["Petal.Length"])
