How to use groupby grouping in Pandas

This article mainly introduces how to use groupby grouping in Pandas, which has a certain reference value, and interested friends can refer to it. I hope you will gain a lot after reading this article.

Groupby grouping import pandas as pdimport numpy as npdf=pd.DataFrame ({'A': ['foo',' bar', 'foo',' foo'],'B': ['one',' one', 'two',' three', 'two',' two' 'one',' three'],'C': np.random.randn (8),'D': np.random.randn (8)) print (df) grouped=df.groupby ('A') print ('-'* 30) print (grouped.count ()) print ('-'* 30) grouped=df.groupby (['A'') 'B']) print (grouped.count ()) print (' -'* 30) # grouped by function def get_letter_type (letter): if letter.lower () in 'aeiou': return'a' else: return 'b'grouped=df.groupby (get_letter_type Axis=1) print (grouped.count ()) A B C D0 foo one 1.429387 0.6435691 bar one-0.858448-0.2130342 foo two 0.375644 0.2145843 bar three 0.042284-0.3304814 foo two-1.421967 0.7681765 bar two 1.293483-0.3990036 foo one-1.101385-0.2363417 foo three-0.852603-1.718694- -B C DA bar 3 3 3foo 5 55-C DA B bar one 1 1 three 1 1 two 1 1foo one 2 2 three 1 1 two 2 2- -a b 0 1 31 1 32 1 33 1 34 1 35 1 36 1 37 1 3se=pd.Series 3) print (se) se.groupby (level=0) 6 19 28 39 48 5dtype: int64# grouping summation grouped=se.groupby (level=0). Sum () print (grouped) 6 18 89 6dtype: int64df2=pd.DataFrame ({'Xray: [' Acho dagger: ['Achuo dagger]],' Yee: [1pint 2jue 3]}) print (df2) X Y0A 11 B 22 A 33 B) And query the data of column A grp=df2.groupby ('X'). Get_group ('A') print (grp) X Y0A12A 3Pandas multilevel index arrays = [['bar',' bar', 'baz',' baz', 'foo',' foo', 'qux',' qux'], ['one',' two', 'one' 'two']] index=pd.MultiIndex.from_arrays (arrays,names= [' first','second']) print (index) MultiIndex ([('bar',' one'), ('bar',' two'), ('baz',' one'), ('baz',' two'), ('foo',' one'), ('foo',' two') ('qux',' one'), ('qux',' two')], names= ['first',' second']) s=pd.Series (np.random.randn (8) Index=index) print (s) first secondbar one 0.120979 two-0.440384baz one 0.515106 two-0.019882foo one 1.149595 two-0.369984qux one-0.930438 two 0.146044dtype: float64# packet Sum grouped=s.groupby (level='first') print (grouped.sum ()) firstbar-0.319405baz 0.495224foo 0.779611qux-0.784394dtype: float64grouped=df.groupby (['A'' ) print (grouped.size ()) A B bar one 1 three 1 two 1foo one 2 three 1 two 2dtype: int64print (df) A B C D0 foo one 1.429387 0.6435691 bar one-0.858448-0.2130342 foo two 0.375644 0.2145843 bar three 0.042284-0.3304814 foo two-1.421967 0.7681765 bar two 1.293483-0.3990036 foo one-1.101385-0.2363417 foo three-0.852603-1.718694print (grouped.describe (). Head ()) C\ count mean std min 25% 75% A B Bar one 1.0-0.858448 NaN-0.858448-0.858448-0.858448-0.858448 three 1.0 0.042284 NaN 0.042284 0.042284 0.042284 two 1.01.293483 NaN 1.293483 1.293483 1.293483 foo one 0.164001 1.789526-1.101385-0.468692 0.164001 0.796694 three 1.0-0.852603 NaN-0.852603-0.852603-0.852603-0.852603 D\ max count mean std min 25% 50% A B bar one-0.858448 1.0-0.213034 NaN-0.213034-0.213034-0.213034 three 0.042284 1.0-0.330481 NaN-0.330481-0.330481-0.330481 two 1.293483 NaN-0.399003-0.399003-0.399003 foo one 1.429387 2.0 0.203614 0.622191-0.236341-0.016364 0.203614 three-0.852603 1.0-1.718694 NaN-1.718694-1.718694-1.718694

75% max

A B

Bar one-0.213034-0.213034

Three-0.330481-0.330481

Two-0.399003-0.399003

Foo one 0.423592 0.643569

Three-1.718694-1.718694

Grouped=df.groupby ('A') grouped ['C'] .agg ([np.sum,np.mean,np.std])

.dataframe tbody tr th:only-of-type {vertical-align: middle;}

.dataframe tbody tr th {vertical-align: top;}. Dataframe thead th {text-align: right;}

Sum mean std A bar 0.477319 0.159106 1.080712 foo-1.570925-0.314185 1.188767

String manipulation import pandas as pdimport numpy as nps=pd.Series (['Achievement recording, baking, recording, caging, writing, etc.) Np.nan]) print (s) # to lowercase print (s.str.lower ()) # to uppercase print (s.str.upper ()) # length of each character print (s.str.len ()) 0 A1 b2 c3 D4 NaNdtype: object0 A1 b2 c3 D4 NaNdtype: object0 A1 B2 C3 D4 NaNdtype: object0 1.01 1.02 1.03 1.04 NaNdtype: float64index=pd.Index (['Index' 'ru',' men']) # remove spaces print (index.str.strip ()) # remove spaces on the left print (index.str.lstrip ()) # remove spaces on the right print (index.str.rstrip ()) Index (['Index',' ru', 'men'], dtype='object') Index ([' Index', 'ru',' men'], dtype='object') Index (['Index',' ru', 'men'] Dtype='object') df=pd.DataFrame (np.random.randn (3jing2), columns= ['An axiom dagger BB'], index=range (3) print (df) An a B b0 3.005273 0.4866961 1.093889 1.0542302-2.846352 0.30246 replacement of print (df.columns.str.replace ('','_') Index (['Aggafia,' Blockb'], dtype='object') s=pd.Series (['astatbC') Print (s) 0 a_b_C1 c_d_e2 f_g_hdtype: objectprint (s.str.split ('_')) 0 [a, b, C] 1 [c, d, e] 2 [f, g, h] dtype: objectprint (s.str.split ('_', expand=True,n=1)) 0 10 a b_C1 c d_e2 f g_hs = pd.Series (['A'') 'rumen','ru','rumen','xiao','zhan']) print (s.str.contains (' ru')) 0 False1 True2 True3 True4 False5 Falsedtype: bools=pd.Series (['axiajiajia | bangzhonga | c']) print (s) 0 A1 a | b2 a | cdtype: objectprint (s.str.get_dummies (sep=' |)) a b c0 1 0 01 1 02 1 01 index s=pd.Series (np.arange (5)) Np.arange (5) [::-1], dtype='int64') s4 03 12 21 30 4dtype: int64print (s > 2]) 1 30 4dtype: int64# isin query index is in a certain range print (s.isin ([1jorm 3])) 4 False3 True2 False1 True0 Truedtype: bool# queries data according to the index print (s [s.isin ([1jue 3]) (4])) 3 11 30 4dtype: int64# constructs a joint index of data s=pd.Series (np.arange (6), index=pd.MultiIndex.from_product ([[1mai 2], ['axie dagger])) print (s) 1 a 0 b 1 c 22 a 3 b 4 c 5dtype: int64print (s.iloc [s.index.isin ([(1) remark b'), (2) ]) 1 b 12 c 5dtype: int64# constructs a time series dates=pd.date_range ('20200920) print (dates) DatetimeIndex ([' 2020-09-20, '2020-09-21,' 2020-09-22, '2020-09-23,' 2020-09-24, '2020-09-25,' 2020-09-26, '2020-09-27'] Dtype='datetime64 [ns]', freq='D') df=pd.DataFrame (np.random.randn (8, 4), index=dates,columns= ['Achilles recalcitrance' ) print (df) A B C D2020-09-20-1.218522 2.067088 0.015009 0.1587802020-09-21-0.546837-0.601178-0.894882 0.1720372020-09-22 0.189848-0.910520 0.196186-0.0734952020-09-23-0.566892 0.899193-0.450925 0.6332532020-09-24 0.038838 1.577004 0.580927 0 . 6090502020-09-25 1.562094 0.020813-0.618859-0.5152122020-09-26-1.333947 0.275765 0.139325 1.1242072020-09-27-1.271748 1.082302 1.036805-1.04120 query column A data print (df ['A']) 2020-09-20-1.2185222020-09-21-0.5468372020-09-22 0.1898482020-09-23-0.5668922020-24 0.0388382020-09-25 1.5620942020-09-26-1.3339472020-09-27-1.271748Freq: d Name: a, dtype: float64# queries numbers less than 0, and values greater than 0 are set to NaNdf.where by default (data print of dfb > a (df.query ('(c))