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):

Keiku

import pandas as pd

df1 = pd.DataFrame({'id': [1, 2, 3]})
df2 = pd.DataFrame({'id': [2, 3, 4]})
set(df1.id).intersection(set(df2.id))
# Out[73]: {2, 3}

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})

iris_df['sepal length (bins)'] = pd.cut(iris_df['sepal length (cm)'], bins=[0, 3, 6, 9], include_lowest=False, right=True)

Keiku

library(stringr)

add_backquotes <- function(x) paste0("`", x, "`")
add_doublequotes <- function(x) paste0("\"", x, "\"")

generate_c_code <- function(x){
  vec <- paste0(add_doublequotes(x), sep=",\n")
  vec_tail <- str_replace(tail(vec, 1), ",\n", "\n")
  vec_head <- head(vec, length(vec) - 1)
  vec <- c(vec_head, vec_tail)

Keiku

library(dplyr)
library(broom)
library(lazyeval)

df <- data_frame(
  group = rep(letters[1:2], each = 50),
  cat1 = letters[round(runif(100) * 5) + 1],
  cat2 = letters[round(runif(100) * 3) + 1]
) 

Keiku

library(dplyr)
library(purrr)
library(broom)

df <- data_frame(
  group = rep(letters[1:2], each = 50),
  cat1 = letters[round(runif(100) * 5) + 1],
  cat2 = letters[round(runif(100) * 3) + 1]
) 

Keiku

# compress/decompress zip file. 
zip file.csv.zip file.csv
unzip file.csv.zip

# compress/decompress gz file. 
gzip file.csv
gzip -d file.csv.gz

# compress/decompress bz2 file. 
bzip2 file.csv

Keiku

library(gplots)
library(dplyr)
library(magrittr)

check_id_sets <- function(ids){
  ids_venn <- gplots::venn(ids, show.plot=FALSE)
  ids_list <- unlist(as.list(ids_venn))
  mat_dim <- c((length(ids_list) / (length(ids)+1)), length(ids)+1)
  id_sets <- ids_list %>%
    matrix(., mat_dim) %>%