五个简单有效的Python清理数据脚本分享

import tabula
#获取文件
pdf_filename = input ("Enter the full path and filename: ")
# 提取PDF的内容
frame = tabula.read_pdf(pdf_filename,  encoding = 'utf-8', pages='all')
#根据内容创建CSV文件
frame.to_csv('pdf_conversion.csv')

from time import strftime
import pandas as pd
import glob
# 定义包含CSV文件的文件夹的路径
path = input('Please enter the full folder path: ')
#确保后面有一个斜杠
if path[:-1] != "/":
    path = path + "/"
#以列表形式获取CSV文件
csv_files = glob.glob(path + '*.csv')
#打开每个CSV文件并合并为一个文件
merged_file = pd.concat( [ pd.read_csv(c) for c in csv_files ] )
#创建新文件
merged_file.to_csv(path + 'merged_{}.csv'.format(strftime("%m-%d-%yT%H:%M:%S")), index=False)
print('Merge complete.')

import pandas as pd
# 获取文件名
filename = input('filename: ')
#定义要检查是否重复的CSV列名
duplicate_header = input('header name: ')
#获取文件的内容
file_contents = pd.read_csv(filename)
# 删除重复的行
deduplicated_data = file_contents.drop_duplicates(subset=[duplicate_header], keep="last", inplace=True)
#创建新文件
deduplicated_data.to_csv('deduplicated_data.csv')

import pandas as pd
#获取文件名并定义列
filename = input('filename: ')
col_to_split = input('column name: ')
col_name_one = input('first new column: ')
col_name_two = input('second new column: ')
#将CSV数据添加到dataframe中
df = pd.read_csv(filename)
# 拆分列
df[[col_name_one,col_name_two]] = df[col_to_split].str.split(",", expand=True)
#创建新csv文件
df.to_csv('split_data.csv')

import pandas as pd
#获取文件名并定义用户输入
left_filename = input('LEFT filename: ')
right_filename = input('RIGHT filename: ')
join_type = input('join type (outer, inner, left, right): ')
join_column_name = input('column name(i.e. Account_ID): ')
#读取文件到dataframes
df_left = pd.read_csv(left_filename)
df_right = pd.read_csv(right_filename)
#加入dataframes
joined_data = pd.merge(left = df_left, right = df_right, how = join_type, on = join_column_name)
#创建新的csv文件
joined_data.to_csv('joined_data.csv')