geojackass

import tabula
import pandas as pd

df = tabula.read_pdf("dir/to/path", pages='all')

#PDFが複数枚になる場合に，複数のテーブルに分割される場合，indexをインクリメントする
df0 = df[0].rename(columns={"水路":"suiro", "加 盟":"kamei","Unnamed: 0":"num","氏 名":"name","Unnamed: 1":"kana","所属名":"school","Unnamed: 2":"school_kana","学年":"grade"}).dropna(how='any')
df0 = df0.loc[:,["suiro","kamei","name","school","grade"]]
df0.head()
df1 = df[1].rename(columns={"水路":"suiro", "加 盟":"kamei","Unnamed: 0":"num","氏 名":"name","Unnamed: 1":"kana","所属名":"school","Unnamed: 2":"school_kana","学年":"grade"}).dropna(how='any')

geojackass

geojackass

#####initial setup######
########################
pacman::p_load(tidyverse, magrittr, stringr)
########################

df <- read.csv('{dir_path}')
#データの確認
head(df)
#データサイズの確認
dim(df)

geojackass

geojackass

geojackass

##############initial setup################
getwd()
lib_pth <- getwd()
print(lib_pth)
#install.packages("tidyverse", lib=lib_pth)
#install.packages("pacman", lib=lib_pth)
#install.packages("stringr", lib=lib_pth)
#install.packages("magrittr", lib=lib_pth)
#install.packages("dplyr", lib=lib_pth)
#install.packages("readxl", lib=lib_pth)

geojackass

##############initial setup################
getwd()
lib_pth <- getwd()
print(lib_pth)
#install.packages("tidyverse", lib=lib_pth)
#install.packages("pacman", lib=lib_pth)
#install.packages("stringr", lib=lib_pth)
#install.packages("magrittr", lib=lib_pth)
#install.packages("estatapi", lib=lib_pth)
############################################

geojackass

##############initial setup################
getwd()
lib_pth <- getwd()
print(lib_pth)
#install.packages("tidyverse", lib=lib_pth)
#install.packages("pacman", lib=lib_pth)
#install.packages("stringr", lib=lib_pth)
#install.packages("magrittr", lib=lib_pth)
#install.packages("estatapi", lib=lib_pth)
############################################

geojackass

食べログEDA

3.6点の壁は本当にあるのか

• Link

スクレイピングのコード

import os
import sys

geojackass

# Configuration file for jupyter-notebook.

#------------------------------------------------------------------------------
# Application(SingletonConfigurable) configuration
#------------------------------------------------------------------------------

## This is an application.

## The date format used by logging formatters for %(asctime)s
#c.Application.log_datefmt = '%Y-%m-%d %H:%M:%S'