1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
def pearsonr_2D(x, y):
"""computes pearson correlation coefficient
where x is a 1D and y a 2D array"""
upper = np.sum((x - np.mean(x,axis=0)) * (y - np.mean(y, axis=0)), axis=0)
lower = np.sqrt(np.sum(np.power(x - np.mean(x,axis=0), 2),axis=0) * np.sum(np.power(y - np.mean(y, axis=0), 2), axis=0))
rho = upper / lower
return rho
A = np.array([[[1,3,4],[4,6,5]],[[5,7,8],[1,2,23]],[[3,9,4],[5,7,5]]])
B = np.array([[[7,1,3],[14,4,2]],[[15,6,1],[6,7,91]],[[3,9,4],[5,7,5]]])
c = pearsonr_2D(A,B)
for i,region in enumerate(region):
print(i,region)
df = pd.DataFrame(columns = ["ebayno", "p_sku", "sale", "sku"])
df = df.append(dframe1.loc[dframe1.p_sku == ps], ignore_index=True)
df = df.append([{'site':site,'MB':mb,'NMB':nmb,'NME':nme,'r2':r2}],ignore_index=True)
来自 <http://blog.csdn.net/zn505119020/article/details/77324029>
合并
df = pd.concat([inputdf,classdf],axis=1)
根据分组统计，对不同行操作
gp_col = 'SITE'
df_max = obs.groupby(gp_col)[species].max()
df_min = obs.groupby(gp_col)[species2].min()
插入列 insert（位置，列名，数据）
df_max.insert(0,"站点",sitename)
DataFrame 切片操作，loc, iloc
print df.loc[1:3, ['total_bill', 'tip']]
print df.loc[1:3, 'tip': 'total_bill']
print df.iloc[1:3, [1, 2]]
print df.iloc[1:3, 1: 3]
来自 <https://blog.csdn.net/ly_ysys629/article/details/55224284>
获取数据框列名
print(df.columns)
获取数据框列
df["column-name"]
选取行
df[df["column-name"]=="spec-name"]
选取数据
df.column[index]
df.ix[0,1]
列表转换成dataframe
df = pd.DataFrame([w1_p,w2_p,w3_p,w4_p],index=['w1_pre','w2_pre','w3_pre','w4_pre'])
修改dataframe的列名
df.columns=['site','time','aqi','so2','no2','pm10','co','o3','pm2_5']
|