Data Analysis using numpy and pandas:
Program:
import numpy as np
x1 = np.array([[1,2,3],[4,5,6]])
print(x1.shape)
x2 = np.array([[1,2,3],[4,5,6]])
x2.shape = (3,2)
print(x2.size)
x11 = np.zeros((5,2), dtype = np.int)
print(x11)
x13 = np.ones([2,2], dtype=int)
x14 = np.arange(10, 20, 2)
x15 = np.arange(10, 20, 0.5)
i1 = np.array([[21,12,43],[54,25,6],[27,8,99]])
print(np.amin(i1,1)) #across rows
print(np.amin(i1,0)) #across cols
i2 = np.array([[20,50,80],[30,60,90],[40,70,100]])
print(np.percentile(i2,100))
print(np.median(i2))
i3 = np.array([[1,2,3],[3,4,5],[4,5,6]])
print(np.mean(i3))
i4 = np.array([1,2,3,4])
print(i4)
print(np.average(i4))
i5 = np.array([1,2,3,4])
print(np.var(i5))
print(np.std(i5))
O/P:
(2, 3)
6
[[0 0]
[0 0]
[0 0]
[0 0]
[0 0]]
[12 6 8]
[21 8 6]
100.0
60.0
3.6666666666666665
[1 2 3 4]
2.5
1.25
1.118033988749895
import pandas as pd
dict1 ={'a':1, 'b':2, 'c':3, 'd':4} # Program to Create Data Frame with two dictionaries
dict2 ={'a':5, 'b':6, 'c':7, 'd':8, 'e':9}
Data = {'first':dict1, 'second':dict2}
a = pd.DataFrame(Data)
print(a)
s1 = pd.Series([1, 3, 4, 5, 6, 2, 9]) # Define series 1
s2 = pd.Series([1.1, 3.5, 4.7, 5.8, 2.9, 9.3]) # Define series 2
s3 = pd.Series(['a', 'b', 'c', 'd', 'e']) # Define series 3
Data1 ={'first':s1, 'second':s2, 'third':s3} # Define Data
dfseries = pd.DataFrame(Data1) # Create DataFrame
print(dfseries)
d1 =[[2, 3, 4], [5, 6, 7]] # Define 2d array 1
d2 =[[2, 4, 8], [1, 3, 9]] # Define 2d array 2
Data ={'first': d1, 'second': d2} # Define Data
df2d = pd.DataFrame(Data) # Create DataFrame
print(df2d)
O/P:
first second
a 1.0 5
b 2.0 6
c 3.0 7
d 4.0 8
e NaN 9
first second third
0 1 1.1 a
1 3 3.5 b
2 4 4.7 c
3 5 5.8 d
4 6 2.9 e
5 2 9.3 NaN
6 9 NaN NaN
first second
0 [2, 3, 4] [2, 4, 8]
1 [5, 6, 7] [1, 3, 9]
Comments