Keiku

library(dplyr)
library(broom)

mtcars %>% 
  group_by(cyl) %>% 
  do(tidy(t(quantile(.$mpg, probs = seq(0, 1, 0.25)))))
# Source: local data frame [3 x 6]
# Groups: cyl [3]
# 
# cyl   X0.  X25.  X50.  X75. X100.

Keiku

freq <- function(df, ...){
  df %<>%
    group_by_(...) %>%
    summarise(count = n()) %>%
    arrange_(.dots = ...) %>%
    ungroup() %>%
    mutate(
      cum_count = cumsum(count),
      percent = count / sum(count),
      cum_percent = cumsum(percent)

Keiku

library(readr)
library(data.table)
library(feather)

object.size(df)
# 1654613472 bytes
system.time(write_csv(df, "df_write_csv.csv"))
# ユーザ   システム       経過  
# 160.540     29.079    200.667
system.time(fwrite(df, "df_fwrite.csv"))

Keiku

library(mlr)

set.seed(123, "L'Ecuyer")

iris.task = classif.task = makeClassifTask(id = "iris-example", data = iris, target = "Species")
resamp = makeResampleDesc("CV", iters = 10L)

lrn = makeLearner("classif.rpart")

control.grid = makeTuneControlGrid() 

Keiku

library(dplyr)
library(lubridate)

df <- data_frame(
  id = c(1, 1, 1, 2, 2, 2),
  ym = c("201512", "201601", "201603", "201512", "201602", "201603")
)

elapsed_months <- function(end, start) {
  12 * (year(end) - year(start)) + (month(end) - month(start))

Keiku

library(dplyr)

data <- data_frame(var = c(0, NA, 2))
data %>% mutate(var = coalesce(var, 1))
data %>% mutate(var = replace(var, which(is.na(var)), 1))
data %>% mutate(var = if_else(is.na(var), 1, var))
# A tibble: 3 × 1
# var
# <dbl>
# 1     0

Keiku

library(mice)
library(purrr)

map_df(airquality, function(x) sum(is.na(x)))
# A tibble: 1 × 6
# Ozone Solar.R  Wind  Temp Month   Day
# <int>   <int> <int> <int> <int> <int>
# 1    37       7     0     0     0     0

Keiku

library(dplyr)
library(tidyr)

iris %>%
  as_data_frame(.) %>%
  select(matches("Petal")) %>%
  summarise_all(.funs = c("01:sum" = "sum",
                          "02:min" = "min", 
                          "03:q25" = "quantile(., 0.25)", 
                          "04:median" = "median", 

Keiku

import os
import glob

# アスタリスクが必要
files = glob.glob('/home/dir1/*.zip')
for file in files:
    print(file)
    print('/home/dir2/' + os.path.basename(file))
# /home/dir1/subset3.zip
# /home/dir2/subset3.zip

Keiku

import pandas as pd
from sklearn import datasets
iris = datasets.load_iris()

iris_df = pd.DataFrame(iris.data, columns=iris.feature_names)
iris_df['species'] = iris.target
mapping = {0 : 'setosa', 1: 'versicolor', 2: 'virginica'}
iris_df = iris_df.replace({'species': mapping})

def freq(data, var):