import urllib.request
import pandas as pd
# Url file Website
url = 'https://......CSV'
# Download file
urllib.request.urlretrieve(
url, "F:\.....A.CSV")
csvFilePath = "F:\.....A.CSV"
df = pd.read_csv(csvFilePath, sep='\t')
rows=[0,1,2,3]
df2 = df.drop(rows, axis=0, inplace=True)
df.to_csv(
r'F:\....New_A.CSV')
I tried doing this in code but it's making columns merge into a single column.
What I'm going to do is remove the top row from the left as shown in the picture.
I found a problem sep='\t' change to sep=','
Replace:
df = pd.read_csv(csvFilePath, sep='\t')
by:
df = pd.read_csv(csvFilePath, sep='\t', skiprows=5)
Related
Need help please.
I have a dataframe that reads rows from Excel and appends to Dataframe if certain columns exist.
I need to add an additional Dataframe if the columns don't exist in a sheet and append filename and sheetname and write all the file names and sheet names for those sheets to an excel file. Also I want the values to be unique.
I tried adding to dfErrorList but it only showed the last sheetname and filename and repeated itself many times in the output excel file
from xlsxwriter import Workbook
import pandas as pd
import openpyxl
import glob
import os
path = 'filestoimport/*.xlsx'
list_of_dfs = []
list_of_dferror = []
dfErrorList = pd.DataFrame() #create empty df
for filepath in glob.glob(path):
xl = pd.ExcelFile(filepath)
# Define an empty list to store individual DataFrames
for sheet_name in xl.sheet_names:
df = pd.read_excel(filepath, sheet_name=sheet_name)
df['sheetname'] = sheet_name
file_name = os.path.basename(filepath)
df['sourcefilename'] = file_name
if "Project ID" in df.columns and "Status" in df.columns:
print('')
*else:
dfErrorList['sheetname'] = df['sheetname'] # adds `sheet_name` into the column
dfErrorList['sourcefilename'] = df['sourcefilename']
continue
list_of_dferror.append((dfErrorList))
df['Status'].fillna('', inplace=True)
df['Added by'].fillna('', inplace=True)
list_of_dfs.append(df)
# # Combine all DataFrames into one
data = pd.concat(list_of_dfs, ignore_index=True)
dataErrors = pd.concat(list_of_dferror, ignore_index=True)
dataErrors.to_excel(r'error.xlsx', index=False)
# data.to_excel("total_countries.xlsx", index=None)
I would like to read multiple excel files and store them into a single pandas dataframe, but I would like one of the columns in the dataframe to be the file name. This is because the file name contains the date (this is monthly data) and I need that information. I can't seem to get the filename, but I'm able to get the excel files into a dataframe. Please help.
import os
import pandas as pd
import fsspec
files = os.listdir("C://Users//6J2754897//Downloads//monthlydata")
paths = "C://Users//6J2754897//Downloads//monthlydata"
a = pd.DataFrame([2], index = None)
df = pd.DataFrame()
for file in range(len(files)):
if files[file].endswith('.xlsx'):
df = df.append(pd.read_excel(paths + "//" + files[file], sheet_name = "information", skiprows=7), ignore_index=True)
df['Month'] = str(files[file])
The order of operations here is incorrect. The line:
df['Month'] = str(files[file])
Is going to overwrite the entire column with the most recent value.
Instead we should only add the value to the current DataFrame:
import os
import pandas as pd
paths = "C://Users//6J2754897//Downloads//monthlydata"
files = os.listdir(paths)
df = pd.DataFrame()
for file in range(len(files)):
if files[file].endswith('.xlsx'):
# Read in File
file_df = pd.read_excel(paths + "//" + files[file],
sheet_name="information",
skiprows=7)
# Add to just this DataFrame
file_df['Month'] = str(files[file])
# Update `df`
df = df.append(file_df, ignore_index=True)
Alternatively we can use DataFrame.assign to chain the column assignment:
import os
import pandas as pd
paths = "C://Users//6J2754897//Downloads//monthlydata"
files = os.listdir(paths)
df = pd.DataFrame()
for file in range(len(files)):
if files[file].endswith('.xlsx'):
# Read in File
df = df.append(
# Read in File
pd.read_excel(paths + "//" + files[file],
sheet_name="information",
skiprows=7)
.assign(Month=str(files[file])), # Add to just this DataFrame
ignore_index=True
)
For general overall improvements we can use pd.concat with a list comprehension over files. This is done to avoid growing the DataFrame (which can be extremely slow). Pathlib.glob can also help with the ability to select the appropriate files:
from pathlib import Path
import pandas as pd
paths = "C://Users//6J2754897//Downloads//monthlydata"
df = pd.concat([
pd.read_excel(file,
sheet_name="information",
skiprows=7)
.assign(Month=file.stem) # We may also want file.name here
for file in Path(paths).glob('*.xlsx')
])
Some options for the Month Column are either:
file.stem will give "[t]he final path component, without its suffix".
'folder/folder/sample.xlsx' -> 'sample'
file.name will give "the final path component, excluding the drive and root".
'folder/folder/sample.xlsx' -> 'sample.xlsx'
I am new to python and trying various things to learn the fundamentals. One of the things that i'm currently stuck on is for loops. I have the following code and am positive it can be built out more efficiently using a loop but i'm not sure exactly how.
import pandas as pd
import numpy as np
url1 = 'https://www.cbssports.com/nfl/stats/player/receiving/nfl/regular/qualifiers/?page=1'
url2 = 'https://www.cbssports.com/nfl/stats/player/receiving/nfl/regular/qualifiers/?page=2'
url3 = 'https://www.cbssports.com/nfl/stats/player/receiving/nfl/regular/qualifiers/?page=3'
df1 = pd.read_html(url1)
df1[0].to_csv ('NFL_Receiving_Page1.csv', index=False) #index false gets rid of index listing that appears as the very first column in the csv
df2 = pd.read_html(url2)
df2[0].to_csv ('NFL_Receiving_Page2.csv', index=False) #index false gets rid of index listing that appears as the very first column in the csv
df3 = pd.read_html(url3)
df3[0].to_csv ('NFL_Receiving_Page3.csv', index=False) #index false gets rid of index listing that appears as the very first column in the csv
df_receiving_agg = pd.concat([df1[0], df2[0], df3[0]])
df_receiving_agg.to_csv('NFL_Receiving_Combined.csv', index=False) #index false gets rid of index listing that appears as the very first column in the csv
I'm ultimately trying to combine the data in the above URL's into a single table in a csv file.
You can try this:
urls = [url1,url2,url3]
df_receiving_agg = pd.DataFrame()
for url in urls:
df = pd.read_html(url)
df_receiving_agg = pd.concat([df_receiving_agg, df])
df_receiving_agg.to_csv('filepath.csv',index=False)
You can do this:
base_url = 'https://www.cbssports.com/nfl/stats/player/receiving/nfl/regular/qualifiers/?page='
dfs = []
for page in range(1, 4):
url = f'{base_url}{page}'
df = pd.read_html(url)
df.to_csv(f'NFL_Receiving_Page{page}.csv', index=False)
dfs.append(df)
df_receiving_agg = pd.concat(dfs)
df_receiving_agg.to_csv('NFL_Receiving_Combined.csv', index=False)
I want to read an excel file, sort the rows , remove duplicate files and re-save the file again
To do that, i have written this script:
import pandas as pd
data = pd.ExcelFile('FILE_NAME.xlsx')
df = data.parse('data')
df.sort_index()
df.drop_duplicates(subset = 'MAKAT', keep='first', inplace=False)
data.close()
print(pd.read_excel(data))
print('**** DONE ****')
in the result, I see the rows on the screen but the file stays with the duplicated rows.
My question is how to save these changes to the same file ?
Change the two lines as below:
df = df.sort_index()
df = df.drop_duplicates(subset = 'MAKAT', keep='first').sort_values(by=['MAKAT'])
df.to_csv('outputfile.csv)
I have lots of big data csv files in terms of countries and I want to merge their column in a single csv file, furthermore, each file has 'Year' as an index and having same in terms of length and numbers. You can see below is a given example of a Japan.csv file.
If anyone can help me please let me know. Thank you!!
Try using:
import pandas as pd
import glob
l = []
path = 'path/to/directory/'
csvs = glob.glob(path + "/*.csv")
for i in csvs:
df = pd.read_csv(i, index_col=None, header=0)
l.append(df)
df = pd.concat(l, ignore_index=True)
This should work. It goes over each file name, reads it and combines everything into one df. You can export this df to csv or do whatever with it. gl.
import pandas as pd
def combine_csvs_into_one_df(names_of_files):
one_big_df = pd.DataFrame()
for file in names_of_files:
try:
content = pd.read_csv(file)
except PermissionError:
print (file,"was not found")
continue
one_big_df = pd.concat([one_big_df,content])
print (file," added!")
print ("------")
print ("Finished")
return one_big_df