Pandas - Revision history

Hdridder: /* Select data */

2026-08-04T14:22:28Z

Select data

← Older revision		Revision as of 14:22, 4 August 2026
Line 163:		Line 163:

	;Get all rows from df1 that have an index that exists in df2		;Get all rows from df1 that have an index that exists in df2
	df = df1[df1.index.isin(df2.index)]		:df = df1[df1.index.isin(df2.index)]
			;Negate like
			:df = df1[~df1.index.isin(df2.index)]

	;Or get all intersectioned indices and select by loc:		;Or get all intersectioned indices and select by loc
	df = df1.loc[~~df1~~.index & df2.index]		:df = df1.loc[df.index.intersection(df2.index)]
	df = df1.~~loc[np~~.~~intersect1d~~(~~df1.index,~~ df2.index)]
	df = ~~df1.loc[~~df1.index.~~intersection~~(df2.index)]		;Better for readibility is to create the indexes first and than filter
			<syntaxhighlight lang=python>
			commen_idx = df1.index.intersection(df2.index)
			df1_only_idx = df1.index.difference(df2.index)
			newdf = df1.loc(df1_only_idx)
			</syntaxhighlight>

	==Use data==		==Use data==

2026-08-04T07:01:57Z

Use data

← Older revision		Revision as of 07:01, 4 August 2026
Line 179:		Line 179:
	print('Found a NaN value')		print('Found a NaN value')
	</syntaxhighlight>		</syntaxhighlight>
			;In multi-column indexes the index is returned as a tuple
			<syntaxhighlight lang=python>for (indexA, indexB), row in df.iterrows():</syntaxhighlight>

	;Print all values for the first row		;Print all values for the first row
	<syntaxhighlight lang=python>		<syntaxhighlight lang=python>

2026-03-24T15:44:18Z

Use data

← Older revision		Revision as of 15:44, 24 March 2026
Line 172:		Line 172:
	==Use data==		==Use data==
	;Print 2 attributes for each row and check for no value		;Print 2 attributes for each row and check for no value
			:pd.isna(value) works for Null, NaN (Nod a number) and NaT (not a time) too.
	<syntaxhighlight lang=python>		<syntaxhighlight lang=python>
	for index, row in df.iterrows():		for index, row in df.iterrows():
	print(row['ColumnA'],row['ColumnB'])		print(row['ColumnA'],row['ColumnB'])
	if np.~~isnan~~(row['ColumnA']):		if ps.isna(row['ColumnA']):
	print('Found a NaN value')		print('Found a NaN value')

	</syntaxhighlight>		</syntaxhighlight>
	;Print all values for the first row		;Print all values for the first row

2025-11-18T12:09:08Z

Modify

← Older revision		Revision as of 12:09, 18 November 2025
Line 58:		Line 58:
	==Modify==		==Modify==

	;df.rename(columns={oldname:newname}, inplace=True)		;<nowiki>df.rename(columns={oldname:newname}, inplace=True)</nowiki>
	:Redefine the column headers (modifies the dataframe itself, nothing is returned)		:Redefine the column headers (modifies the dataframe itself, nothing is returned)

Line 108:		Line 108:
	;df[columna].mask(df[columna] == origvalue , newvalue, inplace=True)		;df[columna].mask(df[columna] == origvalue , newvalue, inplace=True)
	:Change all cells in columa that have origvalue into newvalue (inplace, so in the dataframe itself).		:Change all cells in columa that have origvalue into newvalue (inplace, so in the dataframe itself).


	==Select data==		==Select data==

2025-10-15T06:47:23Z

Excel

← Older revision		Revision as of 06:47, 15 October 2025
Line 323:		Line 323:
	dfdict = pd.read_excel(filename, sheet_name=None)		dfdict = pd.read_excel(filename, sheet_name=None)
	except Exception as exception:		except Exception as exception:
	print(f"{~~file~~} cannot be read by pandas.read_excel as {exception}")		print(f"{filename} cannot be read by pandas.read_excel as {exception}")
	else:		else:
	for sheetname, df in dfdict.items():		for sheetname, df in dfdict.items():

2025-07-07T09:51:36Z

Excel

← Older revision		Revision as of 09:51, 7 July 2025
Line 302:		Line 302:
	:Force columns to be read as string		:Force columns to be read as string
	;read_excel(xlsfile, sheet_name=None)		;read_excel(xlsfile, sheet_name=None)
	:Read all sheets into a dict {sheetname: df,...}.		:Read all sheets into a dict {sheetname: df,...}. Sheets can be specified by number or name, if multiple, in a list. If only 1 sheet is specified a dataframe is returned, not a dict of dataframes.
	<syntaxhighlight lang=python>		<syntaxhighlight lang=python>
	dfdict = pd.read_excel(filename, sheet_name=None)		dfdict = pd.read_excel(filename, sheet_name=None)

2025-06-06T09:50:28Z

@@ Line 17: / Line 17: @@
 Single or multiple columns can be addressed as list like in <code>df.set_index([column1,column2])</code> to set an index over 2 columns.
 ==Information==
 ;df.info()
 :Information on dataframe (Index, size, datatypes per column)
@@ Line 40: / Line 55: @@
 ;df.columnname.dtype
 :Return the data-type of column columnname
 ==Modify==
@@ Line 97: / Line 109: @@
 :Change all cells in columa that have origvalue into newvalue (inplace, so in the dataframe itself).
 ==Select data==

2025-05-20T09:53:16Z

Reading Data

@@ Line 288: / Line 288: @@
 </syntaxhighlight>
 ;read_excel(xlsfile, sheetname)
 :Read data from the sheet with 'sheetname' in a microsoft [[XLS|Excel file]] into a dataframe
@@ Line 304: / Line 312: @@
 </syntaxhighlight>
-;read_csv(csvfile)
+Convert all sheets to CSV files
-:Read data from a file with Character Separated Values
+<syntaxhighlight lang=python>
-;<nowiki>read_csv(csvfile, delimiter=',', usecols=[<columnA>, <columnB>], dtype = {<columnA>: str})</nowiki>
+import sys
-:Read columns <columnA> and <columnB> into a dataframe and force columnA to string type.
+import pandas as pd
-;<nowiki>read_csv(csvfile, index_col=False, header=None, names=['columnA', columnB'], na_values = 'None')</nowiki>
-:Read from a file with no indexcolumn nor a headerrow,  set the colomnnames and handle 'None' and NA value.
+def main():

2025-05-15T10:23:55Z

Reading Data

← Older revision		Revision as of 10:23, 15 May 2025
Line 288:		Line 288:
	</syntaxhighlight>		</syntaxhighlight>

	;read_excel(xlsfile,sheetname)		;read_excel(xlsfile, sheetname)
	:Read data from a microsoft [[XLS\|Excel file]].		:Read data from the sheet with 'sheetname' in a microsoft [[XLS\|Excel file]] into a dataframe
	;<nowiki>read_excel(xlsfile,sheetname,converters={'columna':str,'columnb':str})</nowiki>		;<nowiki>read_excel(xlsfile,sheetname,converters={'columna':str,'columnb':str})</nowiki>
	:Force columns to be read as string		:Force columns to be read as string
			;read_excel(xlsfile, sheet_name=None)
			:Read all sheets into a dict {sheetname: df,...}.
			<syntaxhighlight lang=python>
			dfdict = pd.read_excel(filename, sheet_name=None)
			for sheetname, df in dfdict.items():
			print(f"Working on sheet {sheetname}")
			for index, row in df.iterrows():
			print(row)
			adict = df.to_dict('records') # Creates a list of dicts [{columname: value,...},...]
			print(json.dumps(adict, indent=4))
			</syntaxhighlight>

	;read_csv(csvfile)		;read_csv(csvfile)

2024-09-22T18:23:30Z

Select data

← Older revision		Revision as of 18:23, 22 September 2024
Line 144:		Line 144:
	See also the [https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.str.contains.html#pandas.Series.str.contains pandas series pages]		See also the [https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.str.contains.html#pandas.Series.str.contains pandas series pages]
	;df[df['fieldname'].str.contains('regexp',regex=True)]		;df[df['fieldname'].str.contains('regexp',regex=True)]
	:Select all rows in df where fieldname matches regexp. The field must have a string datetype. If you are looking for a simple string you can leave out the regex=True part.		:Select all rows in df where fieldname contens matches regexp. The field must have a string datetype. If you are looking for a simple string you can leave out the regex=True part.
	;df[df['fieldname'].gt(value)]		;df[df['fieldname'].gt(value)]
	:Select all rows in df where fieldname is bigger than value. The field must have a numeric datetype		:Select all rows in df where fieldname is bigger than value. The field must have a numeric datetype