python代码大全和用法,python,代码命令大全。小编来告诉你更多相关信息。

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

def write_imf(fl_save_path, data):

sh = wb.add_sheet(u\'data\', cell_overwrite_ok=True)

colnames = data.columns.values

for i in range(0, data.shape[1]):

sh.write(0, i, colnames[i])

for i in range(1, len(data) + 1):

for j in range(0, data.shape[1]):

value = data.iloc[i - 1, j]

try:

value.dtype

if value.dtype == \'int64\':

value = int(value)

if value.dtype == \'float64\':

value = float(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):

return True

except:

return False

def get_excel_content(file_path):

wb = xlrd.open_workbook(file_path, encoding_override=\'utf-8\')

wb_cont_imf = []

df = pd.DataFrame(wb_cont_imf[1:], columns=wb_cont_imf[0])

return df

模块2：获取各种时间

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

firstDayWeekDay, monthRange = calendar.monthrange(year, month)

firstDay = datetime.date(year=year, month=month, day=1)

lastDay = datetime.date(year=year, month=month, day=monthRange)

return lastDay

模块3：pd中的dataframe转png

def render_mpl_table(data, col_width=5.0, row_height=0.625, font_size=1,

bbox=[0, 0, 1, 1], header_columns=0,

ax=None,**kwargs):

if ax is None:

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]

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)])

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

_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:

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,

mask=alice_mask,

stopwords=STOPWORDS.add(\"said\")

)

wc.generate(text)

if filename is None:filename=\"词云结果.png\"

wc.to_file(os.path.join(current_file, filename))

def main():

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\'):

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\'

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

_author_ = \'xisuo\'

import urllib.request

import requests

from bs4 import BeautifulSoup

from lxml import etree

import os

response=requests.get(url).text

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):

os.mkdir(save_path)

print(\'img folder create successful\')

for src in src_list:

save_img_path=os.path.join(save_path,\'%d.jpg\'%i)

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

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\')

print(\'开始分组处理KeyTag标签...\')

incomelevel_top = data[data[\'income_level\'] == \'高\']

kw_tag_top = \' \'.join(incomelevel_top[\'kw_tag\'])

print(\'kw_tag_top : \\n\',kw_tag_top)

incomelevel_mid = data[data[\'income_level\'] == \'中\']

kw_tag_mid = \' \'.join(incomelevel_mid[\'kw_tag\'])

print(\'kw_tag_mid : \\n\',kw_tag_mid)

incomelevel_low = data[data[\'income_level\'] == \'低\']

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\')

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\')

kw_tag_value = transformer.get_feature_names()

result_target = pd.DataFrame(kw_tag_value,columns = [\'kw_tag\'])

print(\'result_target : \\n\',result_target)

tf_score = kw_tag_score.toarray()

print(\'tf_score : \\n\',tf_score)

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

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)

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_text=[\'{:.0f}%\'.format(max(values)*100),\'{:.0f}%\'.format(min(values)*100)],

pos_left=\'10%\',

pos_bottom=\'15%\'

),

legend_opts=opts.LegendOpts(is_show=False)

)

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_text=[\'{:.0f}%\'.format(max(values) * 100), \'{:.0f}%\'.format(min(values) * 100)],

pos_left=\'10%\',

pos_bottom=\'5%\'

),

legend_opts=opts.LegendOpts(is_show=False)

)

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)

)

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)