import pandas as pd
import xlrd
import os
import matplotlib.pylab as plt
file_folder_address = 'C:/Users/Amirreza/Desktop/python homeworks/project files'
df_total=pd.DataFrame()
for file in os.listdir(file_folder_address): #os.listdir gives a list of exel file names
df_men_urb = pd.DataFrame()
df_women_urb = pd.DataFrame()
df_men_rural = pd.DataFrame()
df_women_rural = pd.DataFrame()
sheet_names = pd.ExcelFile(os.path.join(file_folder_address, file), engine="xlrd").sheet_names
`
when I use this cod make above error . what should I do ?
Related
I am trying to read data from the following link to a data frame without saving locally (this is important). I figured out a way (below), but is there an efficient way to do this?
from urllib.request import urlopen
import pandas as pd
from io import StringIO
from matplotlib.dates import DateFormatter
from datetime import datetime
uri = 'https://mesonet.agron.iastate.edu/cgi-bin/request/asos.py?station=AXA&data=all&year1=2022&month1=12&day1=1&year2=2022&month2=12&day2=1&tz=Etc%2FUTC&format=onlycomma&latlon=no&elev=no&missing=M&trace=T&direct=no&report_type=3&report_type=4'
data = urlopen(uri, timeout=300).read().decode("utf-8")
dateparse = lambda x: datetime.strptime(x.strip(), '%Y-%m-%d %H:%M')
str1 = data.split('\n')
dfList = []
for ii in range(1,len(str1)):
if len(str1[ii])>0:
df1 = pd.read_csv(StringIO(str1[ii]), parse_dates=[1], date_parser=dateparse, header=None) #Read each string into a dataframe
if not df1.empty:
df2 = df1.iloc[:,0:3] #Get the first five columns
if df2.iloc[0,-1] != 'M': #Don't append the ones with missing data
dfList.append(df2)
df = pd.concat(dfList, axis=0, ignore_index=True)
df.columns = ['Station','Date','Temp']
ax1 = df.plot(x=1,y=2)
ax1.get_figure().autofmt_xdate()
Using requests, pandas and io:
from io import StringIO
import pandas as pd
import requests
url = (
"https://mesonet.agron.iastate.edu/cgi-bin/request/asos.py?"
"station=AXA&data=all&year1=2022&month1=12&day1=1&year2=2022&"
"month2=12&day2=1&tz=Etc%2FUTC&format=onlycomma&latlon=no&"
"elev=no&missing=M&trace=T&direct=no&report_type=3&report_type=4"
)
with requests.Session() as request:
response = request.get(url, timeout=30)
if response.status_code != 200:
print(response.raise_for_status())
df = pd.read_csv(StringIO(response.text), sep=",")
print(df)
import glob
import pandas as pd
import numpy as np
import os
import fnmatch
import zipfile
df1 = pd.read_csv("2016Q12ExactTargetE1.csv",names = ['FileName'])
print("\nRead " ,df1.shape[0] , "Records")
# accessing and printing files in directory and subdirectory
for filename in glob.glob('c:\\temp\\*.zip', recursive=True):
#print(filename)
myzip=filename
zf = zipfile.ZipFile(myzip)
zfl = zf.namelist()
eml_files = fnmatch.filter(zfl, "*.eml")
df2 = pd.DataFrame(eml_files )
print("\nRead2 " ,df2.shape[0] , "Records")
The csv file
FileName
F0B1F7B371C427E6FDDE1078287A3C71.eml
E107A8CADF8F87B05599A3AAF03D5BA1.eml
30B54778C0B912F2516F6C390A137E91.eml
D06DD3162620490F7E9F8ADD1AE0F621.eml
10E3BAFB831EA97615DBBBF18D601EC1.eml
the eml_files looks like
['00E6E77CE9890A3F34343997BCA33791.eml',
'109E4F29239EA8259707B2E3D0D00351.eml',
'403EBEC70C1F305B72EFAA3822D75871.eml',
'30B54778C0B912F2516F6C390A137E91.eml',
'E107A8CADF8F87B05599A3AAF03D5BA1.eml',
'F0B1F7B371C427E6FDDE1078287A3C71.eml',
'00654E78278B0BBDFBF29BAEA3F61051.eml',
'10E3BAFB831EA97615DBBBF18D601EC1.eml',
'30295A4958D6787060A9BD30ABA3BD81.eml',
'712FE30B1D680ACF5F5194E05E7AFCC1.eml',
'80E928FB95A365F85AE1A99DC8418061.eml',
'91681F0020EAC9AC7F010E917CD72F51.eml',
'C0542641286DE272AB1FAEF954BA1951.eml',
'D06DD3162620490F7E9F8ADD1AE0F621.eml',
'214C558DD0ABCAC2EA3BE06DE95E0811.eml',
'4101E93C02FBA028CEA078B9A3542B01.eml',
'51159C8E5965890AE7356E92BC1C6921.eml',
'50775947EFD5010C3D5EA799F36029A1.eml']
How can I compare the two dataframes df1 and df2
Thank you
I tried
df3=df1.compare(df2, keep_equal=True)
but I get an error
Can only compare identically-labeled DataFrame objects
because the df2 is created by zipfile.namelist() which is diffrent from df1 which is read from a csv
I tried this,
import glob
import os
import pandas as pd
import pandas_profiling
from pandas_profiling import ProfileReport
files = glob.glob("D:\home_health_services_current_data\*.csv")
df = pd.DataFrame()
for f in files:
csv = pd.read_csv(f)
df = df.append(csv)
profile = ProfileReport(df, title="Profiling Report", explorative=True)
profile.to_file("D:\proj_report\profilerep\prof_report.html")
i need to read a string like csv content with pandas , but pandas get some errors, i don't knonw what happened, can anyone help me?
import pandas as pd
import io
s = ',测试项,信息,结果\r\n0,软件测试机型805,软件测试机型805,PASS\r\n1,软件当前版本1,软件当前版本1,FAIL\r\n2,软件测试机型805,软件测试机型805,PASS\r\n3,软件当前版本1,软件当前版本1,FAIL\r\n4,软件测试机型805,软件测试机型805,PASS\r\n5,软件当前版本1,软件当前版本1,FAIL\r\n'
buf = io.StringIO()
buf.write(s)
df = pd.read_csv(buf)
got error, EmptyDataError: No columns to parse from file
老铁你拿去
import pandas as pd
import io
s = ',测试项,信息,结果\r\n0,软件测试机型805,软件测试机型805,PASS\r\n1,软件当前版本1,软件当前版本1,FAIL\r\n2,软件测试机型805,软件测试机型805,PASS\r\n3,软件当前版本1,软件当前版本1,FAIL\r\n4,软件测试机型805,软件测试机型805,PASS\r\n5,软件当前版本1,软件当前版本1,FAIL\r\n'
buf = io.StringIO()
buf.write(s)
buf.seek(0)
df = pd.read_csv(buf)
``
I am fetching excel data from django database via raw query. excel is generated but column header is missing .
please suggest some way to get that header.
import pandas as pd
from pandas import ExcelWriter
df1 = pd.DataFrame(row1)
try:
from StringIO import StringIO
except:
from io import StringIO
import xlwt
wb = Workbook()
writer = ExcelWriter("XYZ.xlsx",options={'remove_timezone': True})
xl_out = StringIO()
writer.path = xl_out
ws1 = wb.add_sheet("abc")
for col_num, value in enumerate(df1.columns.values):
ws1.write(1,col_num + 1, 'value')
df1.to_excel(writer,"abc", index= True, header=True)
writer.save()