python_使用笔记

１．循环读取目录下的file

import os
csv_directory="/test/"
for entry in os.listdir(csv_dirctory):
    file_name = os.path.join(csv_dirctory, entry)
    if os.path.isfile(file_name) and not entry.startswith('.'):
        print file_name

２．csv的写入与读取

import csv
file_name="test.csv"
with open(file_name, 'w') as pst_neg:
    writer=csv.DictWriter(pst_neg, header)
    writer.writeheader()
with open(file_name) as f:
    reader = csv.DictReader(f)
    for row in reader: print row.keys()

 ３．pandas和matplotlib使用csv绘制散点图

import pandas as pd
import matplotlib.pyplot as plt
reviews=pd.read_csv(file_name)
plt.figure()
x=reviews['x_axis_key']
y=reviews['y_axis_key']
plt.scatter(x, y)
plt.show()

４．pandas 操纵dataframe, 将某个dataframe中的列拼接到另一个dataframe之后，然后去除重复列

original_csv="original_csv.csv"
original = pd.read_csv(original_csv)
file_list=["file1.csv", "file2.csv"]
for entry in file_list:
    decendant=pd.read_csv(entry, delimiter='\t')
    ret=pd.concat([original, decendant], axis=1)
    original=ret
original=original.drop_duplicates().T.drop_duplicates().T
original.to_csv('after_merge.csv', index=False)