Py PPT 06

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 33

Hands-on Workshop

on
Machine Learning Level-1: Advanced Python & Machine Learning
Foundations
Hands-on Workshop
on
Machine Learning Level-1: Advanced Python & Machine Learning
Foundations
Data Exploration
i ons
at
plic
Ap
PC

Machine Learning

Web
Deve
lopme
nt
Numpy:

Stands for
Numerical Python
General Purpose
Array processing
package

Numpy is the fundamental package for numerical computation with Python, it contains a powerful
N-dimensional array object
Numpy:

NumPy or Numerical Python is a general-purpose array processing python


package for scientific computing.

importing numpy library:

import numpy as np

‘numpy’ is library name ‘np’ is short-form of numpy defined using as function


Array Types:
Creating 1D Numpy arrays:

np.array()
.array() is a function to create
numpy array (array may be “dtype = float” create array data as
1D, 2D or so on) float type

Ex1: Ex2:
2D Array:

b = np.array([(1.5,2,3),
(4,5,6)])

Ex:
import numpy as np
b = np.array([(1.5,2,3), (4,5,6)])

print(type(a))
print(a)
3D Array:

c = np.array([[(1.5,2,3), (4,5,6)],
[(3,2,1), (4,5,6)]])

Ex:
import numpy as np
c = np.array([[(1.5,2,3), (4,5,6)],
[(3,2,1), (4,5,6)]])

print(type(a))
print(a)
Important Functions:

.ndim

.shape
import numpy as np
a = np.array([7,2,9,10])
print(a.shape)
reshape
Numpy Functions:

.zeros( )
np.zeros((shape of array),dtype)

.ones( )
np.ones((shape of array),dtype)

.eye( )
np.ones(No. of rows,dtype)
Numpy Functions:

.random.random( )
np.random.random((shape of array))

.random.randint( )
np.random.randint(start_value,end_value,(shape of array))

.linspace( )
np.linspace(start_value,end_value,no_of_items)
Mathematical Functions:

➔ np.add(x,y)
➔ np.subtract(x,y)
➔ np.multiply(x,y)
➔ np.divide(x,y)
➔ np.mean(x)
➔ np.median(x)
Python Program:
Pandas is an open-source
Python Library

Used for
high-performance data
manipulation and analysis
Series
➔ Series is a one-dimensional array
➔ It consists of a Homogenous Data
A 1 2 3 4
Creating Series in Pandas:

Syntax:
pd.Series(data=[ ], dtype= )

Example:
Types of Data

Numerical Data Categorical Data

Ex: Ex:
● Salary ● Male / Female
● Age ● Yes / No
● Weight ● Rating
Numerical Data

Continuous Discrete SAT Score


Data Data

Data Changes with Data within some


respect to Time numerical Range
Categorical:

Categorical Data

Nominal
Ordinal Data
Data

Categories without Data with


mathematical
weightage
mathematical
weightage
4
Data Frame
DataFrame is a two-dimensional array with heterogeneous data.
Loading .csv File in Python Program

pd.read_csv( ‘titanic.csv’ )

titanic Dataset

Python Code
Data Accessing Methods in Pandas

1. Indexing

2. Slicing

3. Filtering
Indexing Method

Accessing single column Accessing Multiple columns

df[“<column_Name >”] df[[“<column1>”,“<column2>,..”]]

Python Code: Python Code:


Indexing Method

.loc function

Access Rows Access Rows & Columns

df.loc[“row1”] df.loc[[“row1”,“row2”],[“col1”,“col2”]]

Ex: Ex:
Slicing Method

.iloc function ➔ Access Rows & Columns using index range.

df.iloc[ <row_range>,<col_range>]

Python Code
Filtering

➔ Filter the required data based on Logic.

Python Code
Data Exploration Techniques

1. Identifying Unique Elements ➔

2. Value Count ➔

3. Null Value Check ➔

4. Drop Feature ➔

5. Feature Mean ➔

6. Feature Median ➔

7. Feature Mode ➔
Map Function in Pandas:
Syntax:
df[“<column_name”] = df[“<column_name”].map(<function_name>)

Python Code:
Apply Function in Pandas

Syntax:

df[[“<col1”, “<col2”]] = df[[“<col1”, “<col2”]].apply(<function_name>)

Python Code:
Apply using Lambda function in Pandas:

Syntax:

df[[“<col1”, “<col2”]] = df[[“<col1”, “<col2”]] .apply(lambda <arguments>:<expression>)

Python Code:

You might also like