ArrayOperations_Pandas.asciidoc

*In[1]:*

#Numpy operations

*In[2]:*

#Array with Array
#Array with scalar
#Universal Array functions

*In[3]:*

import numpy as np
arr = np.arange(0,11)

*In[4]:*

arr

*Out[4]:* ----array([ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10])----

*In[5]:*

arr+arr

*Out[5]:* ----array([ 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20])----

*In[6]:*

arr - arr

*Out[6]:* ----array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])----

*In[7]:*

arr * arr

*Out[7]:* ----array([ 0, 1, 4, 9, 16, 25, 36, 49, 64, 81, 100])----

*In[8]:*

arr+100

*Out[8]:* ----array([100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110])----

*In[9]:*

arr * 100

*Out[9]:* ----array([ 0, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000])----

*In[10]:*

arr - 100

*Out[10]:* ----array([-100, -99, -98, -97, -96, -95, -94, -93, -92, -91, -90])----

*In[11]:*

1/0

*Out[11]:*

    ---------------------------------------------------------------------------

    ZeroDivisionError                         Traceback (most recent call last)

    <ipython-input-11-9e1622b385b6> in <module>
    ----> 1 1/0


    ZeroDivisionError: division by zero

*In[ ]:*

arr/arr

*In[13]:*

# nan --  no object

*In[14]:*

1/arr

*Out[14]:*

<ipython-input-14-016353831300>:1: RuntimeWarning: divide by zero encountered in true_divide
  1/arr
array([       inf, 1.        , 0.5       , 0.33333333, 0.25      ,
       0.2       , 0.16666667, 0.14285714, 0.125     , 0.11111111,
       0.1       ])----


+*In[15]:*+
[source, ipython3]

arr**2

+*Out[15]:*+
----array([  0,   1,   4,   9,  16,  25,  36,  49,  64,  81, 100])----


+*In[16]:*+
[source, ipython3]

np.sqrt(arr)

+*Out[16]:*+
----array([0.        , 1.        , 1.41421356, 1.73205081, 2.        ,
       2.23606798, 2.44948974, 2.64575131, 2.82842712, 3.        ,
       3.16227766])----


+*In[17]:*+
[source, ipython3]

np.exp(arr)

+*Out[17]:*+
----array([1.00000000e+00, 2.71828183e+00, 7.38905610e+00, 2.00855369e+01,
       5.45981500e+01, 1.48413159e+02, 4.03428793e+02, 1.09663316e+03,
       2.98095799e+03, 8.10308393e+03, 2.20264658e+04])----


+*In[18]:*+
[source, ipython3]

np.max(arr)

+*Out[18]:*+
----10----


+*In[19]:*+
[source, ipython3]

arr.max()

+*Out[19]:*+
----10----


+*In[20]:*+
[source, ipython3]

np.sin(arr)

+*Out[20]:*+
----array([ 0.        ,  0.84147098,  0.90929743,  0.14112001, -0.7568025 ,
       -0.95892427, -0.2794155 ,  0.6569866 ,  0.98935825,  0.41211849,
       -0.54402111])----


+*In[21]:*+
[source, ipython3]

np.log(arr)

+*Out[21]:*+

<ipython-input-21-a67b4ae04e95>:1: RuntimeWarning: divide by zero encountered in log np.log(arr) array([ -inf, 0. , 0.69314718, 1.09861229, 1.38629436, 1.60943791, 1.79175947, 1.94591015, 2.07944154, 2.19722458, 2.30258509])----

*In[22]:*

#Introduction to Pandas
# Open source library built on top of Numpy
# Fast analysis and data cleaning and preparation
# Excel in performance and productively
# Built in visualization features
# data with Wide variety of sources

*In[23]:*

# conda/pip install pandas

*In[24]:*

# Pandas Series

*In[25]:*

import numpy as np
import pandas as pd

*In[26]:*

labels=['a','b','c']
my_data=[10,20,30]
arr=np.array(my_data)
d = {'a':10,'b':20,'c':30}

*In[27]:*

labels

*Out[27]:* ----['a', 'b', 'c']----

*In[28]:*

my_data

*Out[28]:* ----[10, 20, 30]----

*In[29]:*

d

*Out[29]:* ----{'a': 10, 'b': 20, 'c': 30}----

*In[30]:*

pd.Series(data=my_data)

*Out[30]:* ----0 10 1 20 2 30 dtype: int64----

*In[31]:*

arr

*Out[31]:* ----array([10, 20, 30])----

*In[32]:*

pd.Series(data=my_data,index=labels)

*Out[32]:* ----a 10 b 20 c 30 dtype: int64----

*In[33]:*

pd.Series(arr,labels)

*Out[33]:* ----a 10 b 20 c 30 dtype: int64----

*In[34]:*

pd.Series(d)

*Out[34]:* ----a 10 b 20 c 30 dtype: int64----

*In[35]:*

d

*Out[35]:* ----{'a': 10, 'b': 20, 'c': 30}----

*In[36]:*

pd.Series(data=labels)

*Out[36]:* ----0 a 1 b 2 c dtype: object----

*In[41]:*

Ser1=pd.Series([1,2,3,4],['India','US','China','Germany'])

*In[42]:*

Ser1

*Out[42]:* ----India 1 US 2 China 3 Germany 4 dtype: int64----

*In[43]:*

Ser2=pd.Series([1,2,5,4],['India','US','Italy','Germany'])

*In[44]:*

Ser2

*Out[44]:* ----India 1 US 2 Italy 5 Germany 4 dtype: int64----

*In[46]:*

Ser1['US']

*Out[46]:* ----2----

*In[47]:*

Ser1+Ser2

*Out[47]:* ----China NaN Germany 8.0 India 2.0 Italy NaN US 4.0 dtype: float64----

*In[48]:*

Ser3=pd.Series(data=labels)

*In[49]:*

Ser3

*Out[49]:* ----0 a 1 b 2 c dtype: object----

*In[50]:*

Ser3[2]

*Out[50]:* ----'c'----

*In[51]:*

#DataFrames

*In[ ]:*