python之pandas的基本使用(2)
阿新 • • 發佈:2019-01-25
一、排序和排名
排序:sort_index和sort_values函式
程式碼示例:
print 'Series排序' x = Series(range(4), index = ['b', 'a', 'c', 'd']) print x.sort_index() # Series按索引排序 ''' a 1 b 0 c 2 d 3 ''' print x.sort_values() # Series按值排序 ''' b 0 a 1 c 2 d 3 ''' print 'DataFrame按索引排序' frame = DataFrame(numpy.arange(8).reshape((2, 4)), index = ['b', 'a'], columns = list('ABDC')) print frame ''' A B D C b 0 1 2 3 a 4 5 6 7 ''' print frame.sort_index() # 根據行索引來排序 ''' A B D C a 4 5 6 7 b 0 1 2 3 ''' print frame.sort_index(axis = 1) #根據列索引來排序 ''' A B C D b 0 1 3 2 a 4 5 7 6 ''' print frame.sort_index(axis = 1, ascending = False) # 設定降序排序 ''' D C B A b 2 3 1 0 a 6 7 5 4 ''' print 'DataFrame按列的值排序' frame = DataFrame({'b':[4, 7, -3, 2], 'a':[0, 1, 0, 1]}) print frame ''' a b 0 0 4 1 1 7 2 0 -3 3 1 2 ''' print frame.sort_values(by = 'b') # 指定b這列的值進行排序 ''' a b 2 0 -3 3 1 2 0 0 4 1 1 7 ''' print frame.sort_values(by = ['a', 'b']) #先a後b進行列的值排序 ''' a b 2 0 -3 0 0 4 3 1 2 1 1 7 '''
排名:根據值的大小/出現次數來進行排名,得到一組排名值:rank函式
print 'rank:預設升序,排名值從1開始' obj = Series([4, 2, 0, 4],index = ['a','b','c','d']) # 以值從小到大來賦排名值:c:0(1) b:2(2) a:4(3) d:4(4) print obj.rank() ''' a 3.5 求平均值(4+3)/2 b 2.0 c 1.0 d 3.5 ''' print obj.rank(method = 'first') # 按出現順序排名,不求平均值。 ''' a 3.0 b 2.0 c 1.0 d 4.0 ''' print obj.rank(ascending = False, method = 'max') # 逆序,並取排名值最大值。所以-5的rank是7 # a:4(1) d:4(2) b:2(3) c:0(4) ''' dtype: float64 a 2.0 b 3.0 c 4.0 d 2.0 ''' frame = DataFrame({'b':[4.3, 7, -3, 2], 'a':[0, 1, 0, 1], 'c':[-2, 5, 8, -2.5]}) print frame ''' a b c 0 0 4.3 -2.0 1 1 7.0 5.0 2 0 -3.0 8.0 3 1 2.0 -2.5 ''' print frame.rank(axis = 1) # 按行進行排名,預設升序 ''' a b c 0 2.0 3.0 1.0 1 1.0 3.0 2.0 2 2.0 1.0 3.0 3 2.0 3.0 1.0 '''
二、索引重複的情況
程式碼示例:
print '重複索引:進行兩次索引' obj = Series([0,1,2,3,4], index = ['a', 'a', 'b', 'b', 'c']) print obj.index.is_unique # 判斷是非有重複索引 # False print obj['a'][0] # 0 print obj.a[1] # 1 df = DataFrame(numpy.arange(12).reshape(4, 3), index = ['a', 'a', 'b', 'b']) print df ''' 0 1 2 a 0 1 2 a 3 4 5 b 6 7 8 b 9 10 11 ''' print df.ix['b'].ix[0] // 兩次行索引 ''' 0 6 1 7 2 8 Name: b, dtype: int32 ''' print df.ix['b'].ix[1] ''' 0 9 1 10 2 11 Name: b, dtype: int32 '''
三、彙總和計算描述統計
常用方法選項:
常用匯總統計函式 I:
常用匯總統計函式 II:
程式碼示例:
print '求和'
df = DataFrame([[1, numpy.nan], [7, 4], [numpy.nan, numpy.nan], [0, 1]],
index = ['a', 'b', 'c', 'd'],
columns = ['one', 'two'])
print df
'''
one two
a 1.0 NaN
b 7.0 4.0
c NaN NaN
d 0.0 1.0
'''
print df.sum() # 按列求和
# 排除缺失值,skipna預設值為True
'''
one 8.0
two 5.0
dtype: float64
'''
print df.sum(skipna = False)
'''
one NaN
two NaN
'''
print df.sum(axis = 1) # 按行求和
'''
a 1.0
b 11.0
c 0.0
d 1.0
dtype: float64
'''
print '求平均數'
print df.mean(axis = 1, skipna = False)
'''
a NaN
b 5.5
c NaN
d 0.5
'''
print df.mean(axis = 1)
'''
a 1.0
b 5.5
c NaN
d 0.5
'''
print '其它函式'
print df
'''
one two
a 1.0 NaN
b 7.0 4.0
c NaN NaN
d 0.0 1.0
'''
print df.idxmax() # 計算每一列最大值的索引
'''
one b
two b
'''
print df.cumsum() # 每一列的累加和
'''
one two
a 1.0 NaN
b 8.0 4.0
c NaN NaN
d 8.0 5.0
'''
print df.describe() # 對DataFrame每列計算彙總統計
'''
one two
count 3.000000 2.00000
mean 2.666667 2.50000
std 3.785939 2.12132
min 0.000000 1.00000
25% NaN NaN
50% NaN NaN
75% NaN NaN
max 7.000000 4.00000
'''
obj = Series([2,4,8,4], index = ['a', 'a', 'b', 'c'])
print obj.describe() # 對Series計算彙總統計
'''
count 4.000000
mean 4.500000
std 2.516611
min 2.000000
25% 3.500000
50% 4.000000
75% 5.000000
max 8.000000
dtype: float64
'''
四、去重和成員出現計數
主要方法:
print '去重'
obj = Series(['c', 'a', 'd','b', 'b', 'c'])
print obj.unique()
'''
['c' 'a' 'd' 'b']
'''
print obj.value_counts()
'''
b 2
c 2
d 1
a 1
'''
print '判斷元素存在'
mask = obj.isin(['b', 'c'])
print mask
'''
0 True
1 False
2 False
3 True
4 True
5 True
'''
print obj[mask] #只打印元素b和c
'''
0 c
3 b
4 b
5 c
'''
data = DataFrame({'Qu1':[1, 3, 4, 3, 4],
'Qu2':[2, 3, 1, 2, 3],
'Qu3':[1, 5, 2, 4, 4]})
print data
'''
Qu1 Qu2 Qu3
0 1 2 1
1 3 3 5
2 4 1 2
3 3 2 4
4 4 3 4
'''
print data.apply(pd.value_counts).fillna(0)
# 計算每列中各個數字出現的次數,缺失值為0
'''
Qu1 Qu2 Qu3
1 1.0 1.0 1.0
2 0.0 2.0 1.0
3 2.0 2.0 0.0
4 2.0 0.0 2.0
5 0.0 0.0 1.0
'''
print data.apply(pd.value_counts, axis = 1).fillna(0)
# 計算每行中各個數字出現的次數,缺失值為0
'''
1 2 3 4 5
0 2.0 1.0 0.0 0.0 0.0
1 0.0 0.0 2.0 0.0 1.0
2 1.0 1.0 0.0 1.0 0.0
3 0.0 1.0 1.0 1.0 0.0
4 0.0 0.0 1.0 2.0 0.0
'''
五、處理缺失資料
• NaN(Not a Number)表示浮點數和非浮點陣列中的缺失資料,None也被當作NA處理。
處理缺失資料函式:
• dropna 函式:DatFrame預設丟棄任何含有缺失值的行。how引數控制行為,axis引數選擇軸,thresh引數控制NaN數量的要求。
• fillna函式: inplace引數決定返回新物件還是就地修改
程式碼示例:
print '作為null處理的值'
string_data = Series(['a', 'b', numpy.nan, 'd'])
print string_data
'''
0 a
1 b
2 NaN
3 d
'''
print string_data.isnull()
'''
0 False
1 False
2 True
3 False
'''
string_data[0] = None
print string_data
'''
0 None
1 b
2 NaN
3 d
'''
# None也被當作NA處理
print string_data.isnull()
'''
0 True
1 False
2 True
3 False
'''
from numpy import nan as NA
print '丟棄缺失資料NaN'
data = Series([1, NA, 3.5, NA, 7])
print data.dropna()
'''
0 1.0
2 3.5
4 7.0
'''
print 'DataFrame對丟棄NA的處理'
data = DataFrame([[1., 6.5, 3.], [1., NA, NA],
[NA, NA, NA], [NA, 6.5, 3.]])
print data
'''
0 1 2
0 1.0 6.5 3.0
1 1.0 NaN NaN
2 NaN NaN NaN
3 NaN 6.5 3.0
'''
print data.dropna() # 預設只要某行有NA就全部刪除
'''
0 1 2
0 1.0 6.5 3.0
'''
print data.dropna(how = 'all') # 某行全部為NA才刪除
'''
0 1 2
0 1.0 6.5 3.0
1 1.0 NaN NaN
3 NaN 6.5 3.0
'''
data[0] = NA
print data.dropna(axis = 1, how = 'all') #某行有NA就全部刪除
'''
1 2
0 6.5 3.0
1 NaN NaN
2 NaN NaN
3 6.5 3.0
'''
data = DataFrame(numpy.arange(21).reshape(7, 3))
data.ix[:4, 1] = NA
data.ix[:2, 2] = NA
print data
'''
0 1 2
0 0 NaN NaN
1 3 NaN NaN
2 6 NaN NaN
3 9 NaN 11.0
4 12 NaN 14.0
5 15 16.0 17.0
6 18 19.0 20.0
'''
print data.dropna(thresh = 2) # 每行至少要有2個非NA元素則刪除
'''
0 1 2
3 9 NaN 11.0
4 12 NaN 14.0
5 15 16.0 17.0
6 18 19.0 20.0
'''
print '填充0'
df = DataFrame(numpy.arange(9).reshape(3, 3))
df.ix[:1, 1] = NA
df.ix[:2, 2] = NA
print df.fillna(0) # 預設inplace為False
'''
0 1 2
0 0 0.0 0.0
1 3 0.0 0.0
2 6 7.0 0.0
'''
print df
'''
0 1 2
0 0 NaN NaN
1 3 NaN NaN
2 6 7.0 NaN
'''
df.fillna(0, inplace = True) # 就地修改
print df
'''
0 1 2
0 0 0.0 0.0
1 3 0.0 0.0
2 6 7.0 0.0
'''
df = DataFrame(numpy.arange(9).reshape(3, 3))
df.ix[:1, 1] = NA
df.ix[:2, 2] = NA
print '不同行列填充不同的值'
print df.fillna({1:0.5, 2:-1}) # 第3列不存在
'''
0 1 2
0 0 0.5 -1.0
1 3 0.5 -1.0
2 6 7.0 -1.0
'''
print '不同的填充方式'
print df
'''
0 1 2
0 0 NaN NaN
1 3 NaN NaN
2 6 7.0 NaN
'''
print df.fillna(method = 'bfill') # 向前填充
'''
0 1 2
0 0 7.0 NaN
1 3 7.0 NaN
2 6 7.0 NaN
'''
print df.fillna(method = 'bfill', limit = 1) # 只可向前填充一步
'''
0 1 2
0 0 NaN NaN
1 3 7.0 NaN
2 6 7.0 NaN
'''
print '用統計資料填充'
data = Series([1, NA, 2, NA, 3])
print data.fillna(data.mean())
'''
0 1.0
1 2.0
2 2.0
3 2.0
4 3.0
'''
六、多層次化索引
對Series和DataFrame進行多層次的索引MultiIndex,通過stack與unstack進行Series和DataFrame的變換。
程式碼示例:
from pandas import MultiIndex print 'Series的多層次索引' data = Series(numpy.arange(8), index = [['a', 'a', 'b', 'b', 'c', 'c', 'd','d'], [1, 2, 1, 2, 1, 2, 1,2]]) print data # 兩層行索引 ''' a 1 0 2 1 b 1 2 2 3 c 1 4 2 5 d 1 6 2 7 ''' print data.index ''' MultiIndex(levels=[[u'a', u'b', u'c', u'd'], [1, 2]], labels=[[0, 0, 1, 1, 2, 2, 3], [0, 1, 0, 1, 0, 1, 0]]) ''' print data.b ''' 1 2 2 3 ''' print data['b':'c'] # 閉區間 ''' b 1 2 2 3 c 1 4 2 5 ''' print data[:2] # 陣列索引不區分標籤 ''' a 1 0 2 1 ''' print data.unstack() #將Series轉換為DataFrame ''' 1 2 a 0 1 b 2 3 c 4 5 d 6 7 ''' print data.unstack().stack() # 將DataFrame轉換回Series ''' a 1 0 2 1 b 1 2 2 3 c 1 4 2 5 d 1 6 2 7 ''' print print 'DataFrame的多層次化索引' frame = DataFrame(numpy.arange(12).reshape((4, 3)), index = [['a', 'a', 'b', 'b'], [1, 2, 1, 2]], columns = [['A', 'A', 'B'], ['A1', 'A2', 'B1']]) print frame # 兩層行索引和兩層列索引 ''' A B A1 A2 B1 a 1 0 1 2 2 3 4 5 b 1 6 7 8 2 9 10 11 ''' print frame.index ''' MultiIndex(levels=[[u'a', u'b'], [1, 2]], labels=[[0, 0, 1, 1], [0, 1, 0, 1]]) ''' print frame.columns ''' MultiIndex(levels=[[u'A', u'B'], [u'A1', u'A2', u'B1']], labels=[[0, 0, 1], [0, 1, 2]]) ''' frame.index.names = ['key1', 'key2'] frame.columns.names = ['state', 'more'] print frame ''' state A B more A1 A2 B1 key1 key2 a 1 0 1 2 2 3 4 5 b 1 6 7 8 2 9 10 11 ''' print frame.ix['a', 1] ''' A A1 0 A2 1 B B1 2 ''' print frame.ix['a', 1]['B'] ''' more B1 2 ''' print frame.ix['a', 1]['A']['A1'] ''' 0 ''' print print '直接用MultiIndex建立層次索引結構index' print MultiIndex.from_arrays([['A', 'A', 'B'], ['Gree', 'Red', 'Green']], names = ['state', 'color']) ''' MultiIndex(levels=[[u'A', u'B'], [u'Gree', u'Green', u'Red']], labels=[[0, 0, 1], [0, 2, 1]], names=[u'state', u'color']) '''
將索引層進行交換:swaplevel函式。對某個索引層進行排序:sortlevel函式
程式碼示例:
print '索引層交換' frame = DataFrame(numpy.arange(12).reshape((4, 3)), index = [['a', 'a', 'b', 'b'], [1, 2, 1, 2]], columns = [['A', 'A', 'B'], ['A1', 'A2', 'B1']]) frame.index.names = ['key1', 'key2'] print frame ''' A B A1 A2 B1 key1 key2 a 1 0 1 2 2 3 4 5 b 1 6 7 8 2 9 10 11 ''' frame_swapped = frame.swaplevel('key1', 'key2') # 互動索引層 print frame_swapped ''' A B A1 A2 B1 key2 key1 1 a 0 1 2 2 a 3 4 5 1 b 6 7 8 2 b 9 10 11 ''' print frame_swapped.swaplevel(0, 1) # 交換回來 ''' A B A1 A2 B1 key1 key2 a 1 0 1 2 2 3 4 5 b 1 6 7 8 2 9 10 11 ''' print print '對某個索引層進行排序' print frame.sortlevel('key2') ''' A B A1 A2 B1 key1 key2 a 1 0 1 2 b 1 6 7 8 a 2 3 4 5 b 2 9 10 11 ''' print frame.swaplevel(0, 1).sortlevel(0) ''' A B A1 A2 B1 key2 key1 1 a 0 1 2 b 6 7 8 2 a 3 4 5 b 9 10 11 '''
根據某個索引層進行統計計算
程式碼示例:
print '根據索引層進行統計' print frame ''' A B A1 A2 B1 key1 key2 a 1 0 1 2 2 3 4 5 b 1 6 7 8 2 9 10 11 ''' print frame.sum(level = 'key2') ''' A B A1 A2 B1 key2 1 6 8 10 2 12 14 16 '''
將某列轉化為層次的行索引,列名為索引名,列的值為索引值:set_index函式;恢復重置行索引且恢復列:reset_index函式。
程式碼示例:
print '將列索引轉化行層次索引' frame = DataFrame({'a':range(7), 'b':range(7, 0, -1), 'c':['one', 'one', 'one', 'two', 'two', 'two', 'two'], 'd':[0, 1, 2, 0, 1, 2, 3]}) print frame ''' a b c d 0 0 7 one 0 1 1 6 one 1 2 2 5 one 2 3 3 4 two 0 4 4 3 two 1 5 5 2 two 2 6 6 1 two 3 ''' print frame.set_index(['c', 'd']) # 把c/d列索引變成行索引 ''' a b c d one 0 0 7 1 1 6 2 2 5 two 0 3 4 1 4 3 2 5 2 3 6 1 ''' print frame.set_index(['c', 'd'], drop = False) # 列依然保留 ''' a b c d c d one 0 0 7 one 0 1 1 6 one 1 2 2 5 one 2 two 0 3 4 two 0 1 4 3 two 1 2 5 2 two 2 3 6 1 two 3 ''' frame2 = frame.set_index(['c', 'd']) print frame2.reset_index() # 恢復列 ''' c d a b 0 one 0 0 7 1 one 1 1 6 2 one 2 2 5 3 two 0 3 4 4 two 1 4 3 5 two 2 5 2 6 two 3 6 1 '''
七、整數型索引值
Series/DataFrame的索引值的型別為整數時,使用陣列索引會產生歧義:無法分清是陣列型別索引還是字典型別索引。整數型索引的Series/DataFrame索引的方法:以iloc索引替代陣列索引。
程式碼示例:
print '索引值為整數時的歧義'
ser = Series(numpy.arange(3))
print ser
'''
0 0
1 1
2 2
'''
try:
print ser[-1] # 這裡會有歧義.
except:
print 'exception'
ser2 = Series(numpy.arange(3), index = ['a', 'b', 'c'])
print ser2[-1] # 索引值型別不是整數
# 2
ser3 = Series(range(3), index = [-5, 1, 3])
print ser3.iloc[2] # 使用iloc避免直接用[2]產生的歧義
# 2
print
print '對DataFrame使用整數索引'
frame = DataFrame(numpy.arange(6).reshape((3, 2)), index = [2, 0, 1])
print frame
'''
0 1
2 0 1
0 2 3
1 4 5
'''
print frame.iloc[0]
'''
0 4
1 5
'''
# print frame[2] 有歧義則會發生異常錯誤
# print frame['2'] 不存在'2'該索引
print frame.iloc[:, 1]
'''
2 1
0 3
1 5
'''