Keiku

from collections import OrderedDict

d = {'A': 3,
     'B': 2,
     'C': 1}

OrderedDict(sorted(d.items(), key=lambda x: x[0])).values()
# Out[1]: odict_values([3, 2, 1])
OrderedDict(sorted(d.items(), key=lambda x: x[1])).values()
# Out[2]: odict_values([1, 2, 3])

Keiku

from sklearn.preprocessing import LabelEncoder, OneHotEncoder

X_str = np.array([['a', 'dog', 'red'], ['b', 'cat', 'green']])
# transform to integer
X_int = LabelEncoder().fit_transform(X_str.ravel()).reshape(*X_str.shape)
# transform to binary
X_bin = OneHotEncoder().fit_transform(X_int).toarray()

print(X_bin)
# [[ 1.  0.  0.  1.  0.  1.]

Keiku

text = ['This is a string', 'This is another string', 'TFIDF computation calculation', 'TfIDF is the product of TF and IDF']

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(max_df=1.0, min_df=1, stop_words='english', norm = None)

X = vectorizer.fit_transform(text)
X_vovab = vectorizer.get_feature_names()
# Out[1]: ['calculation', 'computation', 'idf', 'product', 'string', 'tf', 'tfidf']
X_mat = X.todense()
# Out[2]:

Keiku

# パッケージをインストールする
pkgs <- c("dplyr", "rpart", "rpart.plot", "rattle", "mlr", "evtree")
install.packages(pkgs, quiet = TRUE)

# パッケージを読み込む
library("dplyr")
library("rattle")
library("mlr")
library("evtree")

Keiku

library(dplyr)
library(lazyeval)

df <- data_frame(group = c(1, 2, 2, 3, 3, 3))

g <- "group"

df %>%
  group_by_(g) %>%
  summarise_(

Keiku

import pandas as pd

df = pd.DataFrame({'A':['A1', 'A2', 'A3'], 'B':[None, 'B2', None]})
df
# Out[51]:
#     A     B
# 0  A1  None
# 1  A2    B2
# 2  A3  None

Keiku

options(scipen = 100, dplyr.width = Inf, dplyr.print_max = Inf)

'%nin%' <- Negate('%in%')
keep_vecs <- function(x, y) x[x %in% y]
drop_vecs <- function(x, y) x[!x %in% y] 
keep_vars <- function(.data, x) dplyr::select_(.data, .dots = x)
drop_vars <- function(.data, x) dplyr::select(.data, -one_of(x)) 

intersect_all <- function(...) Reduce(intersect, list(...))
union_all <- function(...) Reduce(union, list(...))

Keiku

library(dplyr)

iris_df <- as_data_frame(iris)
iris_df %>% rename_(.dots = setNames(names(.), toupper(names(.)))) %>% head(2)
# A tibble: 2 × 5
# SEPAL.LENGTH SEPAL.WIDTH PETAL.LENGTH PETAL.WIDTH SPECIES
# <dbl>       <dbl>        <dbl>       <dbl>  <fctr>
# 1          5.1         3.5          1.4         0.2  setosa
# 2          4.9         3.0          1.4         0.2  setosa

Keiku

library("dplyr")
library("tidyr")
library("data.table")

smp <- data_frame(
  ID = rep(1:3, 2),
  BMI = rep(c(21, 26), 3),
  sbp = rep(c(150, 120), 3),
  nendo = rep(2008:2009, 3)
)

Keiku

a <- c(1, 3, 5, 7, 9)
b <- c(3, 6, 8, 9, 10)
c <- c(2, 3, 4, 5, 7, 9)

intersect_all <- function(...) Reduce(intersect, list(...))
union_all <- function(...) Reduce(union, list(...))

intersect_all(a, b, c)
# [1] 3 9
union_all(a, b, c)