In [1]:
import numpy as np
In [2]:
a = np.array([0,1,2,3,4,5,6,7,8,9])
In [4]:
type(a)
Out[4]:
In [6]:
b = []
for i in a :
b.append(i * 2)
b
Out[6]:
In [7]:
a * 2
Out[7]:
In [9]:
b = np.array([[0, 1, 2], [3, 4, 5]])
b
Out[9]:
In [11]:
print (a.ndim)
print (a.shape)
In [13]:
x = np.arange(3)
x
Out[13]:
In [15]:
y = np.arange(5)
y
Out[15]:
In [16]:
X, Y = np.meshgrid(x,y)
In [17]:
X
Out[17]:
In [18]:
[zip(x, y) for x, y in zip(X, Y)]
Out[18]:
In [19]:
%%writefile ~/data/sample1.csv
c1, c2, c3
1, 1.11, one
2, 2.22, two
3, 3.33, three
In [21]:
import pandas as pd
pd.read_csv('~/data/sample1.csv')
Out[21]:
In [23]:
df = pd.DataFrame(np.arange(10, 22).reshape(3, 4),
index=["a", "b", "c"],
columns=["A", "B", "C", "D"])
df
Out[23]:
In [25]:
df.loc["a", "D"]
Out[25]:
In [26]:
df.loc["a",:]
Out[26]:
In [29]:
df[1:2]
Out[29]:
In [36]:
df.iloc[2:]
Out[36]:
In [37]:
s = pd.Series(range(10))
s[3] = np.nan
In [38]:
s.count()
Out[38]:
In [39]:
df.apply(lambda x: x.max() - x.min())
Out[39]:
In [40]:
np.random.seed(0)
df4 = pd.DataFrame(np.random.randint(1, 10, (8, 4)),
columns=[["A", "A", "B", "B"], ["C", "D", "C", "D"]],
index=[["M", "M", "M", "M", "F", "F", "F", "F"], ["ID" + str(i) for i in range(4)] * 2])
df4.columns.names = ["Cdx1", "Cdx2"]
df4.index.names = ["Rdx1", "Rdx2"]
df4
Out[40]:
In [41]:
df4.stack("Cdx1")
Out[41]:
In [43]:
df4.unstack("Rdx2")
Out[43]: