技巧篇：常用的python代码汇总
一些常用的python代码合集，方便检索引用
模块1：读写excel文件
from datetime import datetime
import odps
import xlwt
import os
from odps import DataFrame
import pandas as pd
import xlrd
import numpy as np
from collections import defaultdict
from collections import Counter
# 写入工作簿
def write_imf(fl_save_path, data):
wb = xlwt.Workbook(encoding='utf-8') # 不写encoding会出现编码错误
sh = wb.add_sheet(u'data', cell_overwrite_ok=True)
# 表头部分,单独写
colnames = data.columns.values
for i in range(0, data.shape[1]):
sh.write(0, i, colnames[i])
# 表内容,循环写入,好像没简便的方法
for i in range(1, len(data) + 1):
for j in range(0, data.shape[1]):
value = data.iloc[i - 1, j]
# print(value)
# 这里的坑特别多！！！数据读进来之后就成numpy.xxx64的类型了，在dataframe的时候就需要统一干掉！
try:
value.dtype
if value.dtype == 'int64':
value = int(value)
# print('value is:%d,type is:%s'%(value,type(value)))
if value.dtype == 'float64':
value = float(value)
# print('value is:%d,type is:%s' % (value, type(value)))
except(RuntimeError, TypeError, NameError, ValueError, AttributeError):
pass
sh.write(i, j, value)
wb.save(fl_save_path)
print('congratulation save successful!')
def save_pd_to_csv(fl_save_path, data):
try:
# 直接转csv不加encoding，中文会乱码
data.to_csv(fl_save_path, encoding="utf_8_sig", header=True, index=False) # 存储
return True
except:
return False
def get_excel_content(file_path):
# 获取excel内的SQL语句，需要通过xlrd获取workbook中的SQL内容，或者读txt，后续改为配置文件
wb = xlrd.open_workbook(file_path, encoding_override='utf-8')
sht = wb.sheet_by_index(0) # 默认第一个工作表
# print(sht.name)
wb_cont_imf = []
nrows = sht.nrows # 行数
wb_cont_imf = [sht.row_values(i) for i in range(0, nrows)] # 第一个工作表内容按行循环写入
df = pd.DataFrame(wb_cont_imf[1:], columns=wb_cont_imf[0])
return df
模块2：获取各种时间
# 获取年月第一天最后一天
def getMonthFirstDayAndLastDay(year=None, month=None):
"""
:param year: 年份，默认是本年，可传int或str类型
:param month: 月份，默认是本月，可传int或str类型
:return: firstDay: 当月的第一天，datetime.date类型
lastDay: 当月的最后一天，datetime.date类型
"""
if year:
year = int(year)
else:
year = datetime.date.today().year
if month:
month = int(month)
else:
month = datetime.date.today().month
# 获取当月第一天的星期和当月的总天数
firstDayWeekDay, monthRange = calendar.monthrange(year, month)
# 获取当月的第一天
firstDay = datetime.date(year=year, month=month, day=1)
lastDay = datetime.date(year=year, month=month, day=monthRange)
# return firstDay, lastDay
return lastDay
模块3：pd中的dataframe转png
# dataframe2png
def render_mpl_table(data, col_width=5.0, row_height=0.625, font_size=1,
header_color='#40466e', row_colors=['#f1f1f2', 'w'], edge_color='w',
bbox=[0, 0, 1, 1], header_columns=0,
ax=None,**kwargs):
if ax is None:
# size = (np.array(data.shape[::-1]) + np.array([0, 1])) * np.array([col_width, row_height])
# fig, ax = plt.subplots(figsize=size)
fig, ax = plt.subplots() # 创建一个空的绘图区
# 衍生知识点，服务器上安装中文字体
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
# plt.rcParams['font.sans-serif'] = ['WenQuanYi Zen Hei Mono']
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.style.use('ggplot')
ax.axis('off')
mpl_table = ax.table(cellText=data.values, bbox=bbox, colLabels=data.columns, **kwargs)
mpl_table.auto_set_font_size(False)
mpl_table.set_fontsize(font_size)
for k, cell in six.iteritems(mpl_table._cells):
cell.set_edgecolor(edge_color)
nrow = k[0]
ncol = k[1]
# 设置表格底色
if nrow == 0 or ncol < header_columns:
cell.set_text_props(weight='bold', color='w')
cell.set_facecolor(header_color)
else:
cell.set_facecolor(row_colors[k[0] % len(row_colors)])
# # 对当日异常数据为0的部分，着重体现
# row_num = []
# for k, cell in mpl_table._cells.items():
# nrow = k[0]
# ncol = k[1]
# val = cell.get_text().get_text()
# if nrow > 0 and ncol == 2 and val != '0':
# row_num.append(nrow)
# for k, cell in six.iteritems(mpl_table._cells):
# nrow = k[0]
# # 设置表格底色
# if nrow in row_num:
# cell.set_facecolor('gold')
# 保留原图的设置
# fig.set_size_inches(width/100.0,height/100.0)#输出width*height像素
plt.gca().xaxis.set_major_locator(plt.NullLocator())
plt.gca().yaxis.set_major_locator(plt.NullLocator())
plt.subplots_adjust(top=1, bottom=0, left=0, right=1, hspace=0, wspace=0)
plt.margins(0, 0)
return ax
模块4：绘制词云
#!/user/bin/python
# -*- coding:utf-8 -*-
_author_ = 'xisuo'
import datetime
import calendar
import xlwt
import os
import pandas as pd
import xlrd
import openpyxl
import numpy as np
from collections import defaultdict
import platform
from wordcloud import WordCloud,STOPWORDS
import matplotlib.pyplot as plt
from PIL import Image
def create_wordcloud(docs=None,imgs=None,filename=None):
'''
:param docs:读入词汇txt，尽量不重复
:param imgs: 读入想要生成的图形，网上随便找
:param filename: 保存图片文件名
:return:
'''
# Read the whole text.
text = open(os.path.join(current_file, docs)).read()
alice_mask = np.array(Image.open(os.path.join(current_file, imgs)))
print(font_path)
wc = WordCloud(background_color="white",
max_words=2000,
font_path=font_path, # 设置字体格式，如不设置显示不了中文
mask=alice_mask,
stopwords=STOPWORDS.add("said")
)
# generate word cloud
wc.generate(text)
# store to file
if filename is None:filename="词云结果.png"
wc.to_file(os.path.join(current_file, filename))
def main():
docs='demo.txt' #读入的文本
imgs="eg.jpg" #需要绘制的图像
filename='res_eg.png' #保存图片文件名
create_wordcloud(docs=docs,imgs=imgs,filename=filename)
print('create wordcloud successful')
if __name__ == '__main__':
start_time = datetime.datetime.now()
print('start running program at:%s' % start_time)
systemp_type = platform.system()
if (systemp_type == 'Windows'):
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
font_path='simfang.ttf'
try:
current_path = os.getcwd()
except:
current_path = os.path.dirname(__file__)
current_file = os.path.join(current_path, 'docs')
current_file = current_path
elif (systemp_type == 'Linux'):
font_path = 'Arial Unicode MS.ttf'
plt.rcParams['font.family'] = ['Arial Unicode MS'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
current_file = '/home/xisuo/mhc_work/docs/' # 服务器上的路径
else:
quit()
if not os.path.exists(current_file):
os.mkdir(current_file)
print('目录中部存在docs文件夹，完成新文件夹创建过程。')
print('当前操作系统：%s，文件存储路径为：%s' % (systemp_type, current_file))
main()
end_time = datetime.datetime.now()
tt = end_time - start_timepython
print('ending time:%s', end_time)
print('this analysis total spend time:%s' % tt.seconds)
模块5：下载ppt素材
#!/user/bin/python
#-*- coding:utf-8 -*-
_author_ = 'xisuo'
import urllib.request
import requests
from bs4 import BeautifulSoup
from lxml import etree
import os
url='http://www.pptschool.com/1491.html'
response=requests.get(url).text
# soup=BeautifulSoup(response,'lxml')
# cont=soup.find('article', class_='article-content')
html=etree.HTML(response)
src_list=html.xpath('//div/article/p/img/@src')
current_path=os.path.dirname(__file__)
save_path=os.path.join(current_path,'ppt_img')
if os.path.exists(save_path):
pass
else:
os.mkdir(save_path)
print('img folder create successful')
i=1
for src in src_list:
save_img_path=os.path.join(save_path,'%d.jpg'%i)
try:
with open(save_img_path,'wb') as f:
f.write(urllib.request.urlopen(src).read())
f.close()
i=i+1
print('save true')
except Exception as e:
print('save img fail')
模块6：模型存储和读取
rom sklearn import joblib
from sklearn import svm
from sklearn2pmml import PMMLPipeline, sklearn2pmml
import pickle
def save_model(train_X,train_y):
''''
save model
:return:
'''
clf = svm.SVC()
clf.fit(X, y)
joblib.dump(clf, "train_model.m")
sklearn2pmml(clf, "train_model.pmml")
with open('train_model.pickle', 'wb') as f:
pickle.dump(clf, f)
return True
def load_model():
'''
laod model
:return:
'''
clf_joblib=joblib.load('train_model.m')
clf_pickle== pickle.load(open('linearregression.pickle','rb'))
return clf_joblib,clf_pickle
模块7：TF-IDF
import time
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
# 读取数据 - 性能不好待优化
print('开始读取KeyTag标签...')
read_data_path = 'D:/untitled/incomelevel_kwtag_20190801.txt'
load_data = pd.read_csv(read_data_path, sep='\t',encoding='utf-8')
data = pd.DataFrame(load_data,columns = ['income_level','kw_tag'])
print('...读取KeyTag标签完成')
# 将数据分组处理
print('开始分组处理KeyTag标签...')
# 高收入
incomelevel_top = data[data['income_level'] == '高']
incomelevel_top = incomelevel_top.head() #test
kw_tag_top = ' '.join(incomelevel_top['kw_tag'])
print('kw_tag_top : \n',kw_tag_top)
# 中收入
incomelevel_mid = data[data['income_level'] == '中']
incomelevel_mid = incomelevel_mid.head() #test
kw_tag_mid = ' '.join(incomelevel_mid['kw_tag'])
print('kw_tag_mid : \n',kw_tag_mid)
# 低收入
incomelevel_low = data[data['income_level'] == '低']
incomelevel_low = incomelevel_low.head() #test
kw_tag_low = ' '.join(incomelevel_low['kw_tag'])
print('kw_tag_low : \n',kw_tag_low)
print('...分组处理KeyTag标签完成')
# 开始加载TF-IDF
vectorizer = CountVectorizer()
result = vectorizer.fit_transform([kw_tag_top, kw_tag_mid, kw_tag_low])
transformer = TfidfVectorizer()
kw_tag_score = transformer.fit_transform([kw_tag_top, kw_tag_mid, kw_tag_low])
print('...KeyTag分词结束')
# 获取全量标签
kw_tag_value = transformer.get_feature_names()
result_target = pd.DataFrame(kw_tag_value,columns = ['kw_tag'])
print('result_target : \n',result_target)
# 分词得分处理
tf_score = kw_tag_score.toarray()
print('tf_score : \n',tf_score)
kw_tag_score_top = pd.DataFrame(tf_score[0],columns = ['kw_tag_score_top']) # 217
kw_tag_score_mid = pd.DataFrame(tf_score[1],columns = ['kw_tag_score_mid'])
kw_tag_score_low = pd.DataFrame(tf_score[2],columns = ['kw_tag_score_low'])
print(len(kw_tag_score_top))
模块8：生成省市地图
import time
import pandas as pd
import xlrd
import re
import matplotlib.pyplot as plt
import six
import numpy as np
# 载入ppt和pyecharts相关的包
from pyecharts.render import make_snapshot
from snapshot_phantomjs import snapshot
from pyecharts import options as opts
from collections import defaultdict
from pyecharts.charts import Bar, Geo, Map, Line,Funnel,Page
import os
from example.commons import Faker
def create_zjs_map():
folder_path = os.getcwd()
file_name = "白皮书数据地图.xlsx"
file_path = os.path.join(folder_path, file_name)
dat = get_excel_content(file_path, sheet_name="省份地图")
df = dat[['城市', '渗透率']]
df.columns = ['city', 'penarate']
print(df)
# df['city'] = df['city'].apply(lambda x: reg.sub('', x))
citys = df['city'].values.tolist()
values = df['penarate'].values.tolist()
print(citys)
print('{:.0f}%'.format(max(values)*100),'{:.0f}%'.format(min(values)*100))
city_name='浙江'
penetration_map = (
Map(init_opts=opts.InitOpts(width='1200px', height='1000px', bg_color='white'))
.add("{}透率分布".format(city_name), [list(z) for z in zip(citys, values)], city_name)
.set_series_opts(
label_opts=opts.LabelOpts(
is_show=True,
font_size=15
)
)
.set_global_opts(
visualmap_opts=opts.VisualMapOpts(
is_show=True,
max_=max(values),
min_=min(values),
is_calculable=False,
orient='horizontal',
split_number=3,
range_color=['#C2D5F8', '#88B0FB', '#4D8AFD'],
range_text=['{:.0f}%'.format(max(values)*100),'{:.0f}%'.format(min(values)*100)],
pos_left='10%',
pos_bottom='15%'
),
legend_opts=opts.LegendOpts(is_show=False)
)
)
# penetration_map.render()
make_snapshot(snapshot, penetration_map.render(), "zj_map.png")
print('保存 zj_map.png')
return penetration_map
def create_county_map(city_name):
folder_path = os.getcwd()
file_name = "白皮书数据地图.xlsx"
file_path = os.path.join(folder_path, file_name)
dat = get_excel_content(file_path, sheet_name="城市地图")
df = dat[['city', 'county', 'penarate']][dat.city == city_name]
citys = df['county'].values.tolist()
values = df['penarate'].values.tolist()
max_insurance = max(values)
print(citys)
province_penetration_map = (
Map(init_opts=opts.InitOpts(width='1200px', height='1000px', bg_color='white'))
.add("{}透率分布".format(city_name), [list(z) for z in zip(citys, values)], reg.sub('',city_name))
.set_series_opts(
label_opts=opts.LabelOpts(
is_show=True,
font_size=15
)
)
.set_global_opts(
visualmap_opts=opts.VisualMapOpts(
is_show=True,
max_=max(values),
min_=min(values),
is_calculable=False,
orient='horizontal',
split_number=3,
range_color=['#C2D5F8', '#88B0FB', '#4D8AFD'],
range_text=['{:.0f}%'.format(max(values) * 100), '{:.0f}%'.format(min(values) * 100)],
pos_left='10%',
pos_bottom='5%'
),
legend_opts=opts.LegendOpts(is_show=False)
)
)
# insurance_map.render()
make_snapshot(snapshot, province_penetration_map.render(), "city_map_{}.png".format(city_name))
print('保存 city_map_{}.png'.format(city_name))
return province_penetration_map
def create_funnel_label():
folder_path=os.getcwd()
file_name = "白皮书数据地图.xlsx"
file_path = os.path.join(folder_path, file_name)
dat = get_excel_content(file_path, sheet_name="漏斗图")
df = dat[['category', 'cnt']]
print(df)
category = df['category'].values.tolist()
values = df['cnt'].values.tolist()
funnel_map = (
Funnel(init_opts=opts.InitOpts(width='1200px', height='1000px', bg_color='white'))
.add("漏斗图", [list(z) for z in zip(category, values)])
.set_series_opts(
label_opts=opts.LabelOpts(
position='inside',
font_size=16,
)
)
.set_global_opts(
legend_opts=opts.LegendOpts(is_show=False)
)
)
# insurance_map.render()
make_snapshot(snapshot, funnel_map.render(), "funnel.png")
print('保存 funnel.png')
return funnel_map
city_list=['温州市','杭州市','绍兴市','嘉兴市','湖州市','宁波市','金华市','台州市','衢州市','丽水市','舟山市']
for city_name in city_list:
create_county_map(city_name)
关于Python学习资料：
在学习python中有任何困难不懂的可以微信扫描下方CSDN官方认证二维码加入python交流学习
多多交流问题，互帮互助，这里有不错的学习教程和开发工具。
（python兼职资源+python全套学习资料）
一、Python所有方向的学习路线
Python所有方向的技术点做的整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。
二、Python必备开发工具
四、Python视频合集
观看零基础学习视频，看视频学习是最快捷也是最有效果的方式，跟着视频中老师的思路，从基础到深入，还是很容易入门的。
五、实战案例
光学理论是没用的，要学会跟着一起敲，要动手实操，才能将自己的所学运用到实际当中去，这时候可以搞点实战案例来学习。
六、Python练习题
检查学习结果。
七、面试资料
我们学习Python必然是为了找到高薪的工作，下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料，并且有阿里大佬给出了权威的解答，刷完这一套面试资料相信大家都能找到满意的工作。
最后，千万别辜负自己当时开始的一腔热血，一起变强大变优秀。