
import pandas as pd # importing pandas as pd
import numpy  as np # importing numpy as np


### Pandas Version


pd.__version__

'1.1.3'


nums = [1, 2, 3, 4,5]
s = pd.Series(nums)
print(s)

0    1
1    2
2    3
3    4
4    5
dtype: int64


s.index

RangeIndex(start=0, stop=5, step=1)


list(s.index)

[0, 1, 2, 3, 4]


nums = [1, 2, 3, 4, 5]
s = pd.Series(nums, index=[1, 2, 3, 4, 5])
print(s)

1    1
2    2
3    3
4    4
5    5
dtype: int64


s.index

Int64Index([1, 2, 3, 4, 5], dtype='int64')


nums = [1, 2, 3, 4, 5]
s = pd.Series(nums, index=['A', 'B', 'C', 'D', 'E'])
print(s)

A    1
B    2
C    3
D    4
E    5
dtype: int64


s.index

Index(['A', 'B', 'C', 'D', 'E'], dtype='object')


fruits = ['Orange','Banana','Mango']
fruits = pd.Series(fruits, index=[1, 2, 3])
print(fruits)

1    Orange
2    Banana
3     Mango
dtype: object


fruits = ['Orange','Banana','Mango']
fruits = pd.Series(fruits, index=['O', 'B', 'M'])
print(fruits)

O    Orange
B    Banana
M     Mango
dtype: object


dct = {'name':'Asabeneh','country':'Finland','city':'Helsinki'}
s = pd.Series(dct)
print(s)

name       Asabeneh
country     Finland
city       Helsinki
dtype: object


dct = {'name':'Asabeneh','country':'Finland','city':'Helsinki'}
s = pd.Series(dct)
print(s)

name       Asabeneh
country     Finland
city       Helsinki
dtype: object


s = pd.Series(10, index = [1, 2, 3])
print(s)

1    10
2    10
3    10
dtype: int64


s = pd.Series(np.linspace(5, 20, 10)) # linspace(starting, end, items)
print(s)

0     5.000000
1     6.666667
2     8.333333
3    10.000000
4    11.666667
5    13.333333
6    15.000000
7    16.666667
8    18.333333
9    20.000000
dtype: float64


nums = [1, 2, 3]
s = pd.Series(nums, index =['A','B','C'])
print(s)

A    1
B    2
C    3
dtype: int64


s['A']

1


s['C']

3


# if we don't pass value to the index argument, the index of the pandas eries will start from zero
nums = [1, 2, 3]
s = pd.Series(nums)
print(s)

0    1
1    2
2    3
dtype: int64


s[0]

1


s[2]

3


copied_fruits = fruits.copy()
copied_fruits

O    Orange
B    Banana
M     Mango
dtype: object


data = [
    ['Asabeneh', 'Finland', 'Helsink'], 
    ['David', 'UK', 'London'],
    ['John', 'Sweden', 'Stockholm']
]
df = pd.DataFrame(data, columns=['Names','Country','City'])
df


data = {'Name': ['Asabeneh', 'David', 'John'], 'Country':[
    'Finland', 'UK', 'Sweden'], 'City': ['Helsiki', 'London', 'Stockholm']}
df = pd.DataFrame(data)
df


data = [
    {'Name': 'Asabeneh', 'Country': 'Finland', 'City': 'Helsinki'},
    {'Name': 'David', 'Country': 'UK', 'City': 'London'},
    {'Name': 'John', 'Country': 'Sweden', 'City': 'Stockholm'}]
df = pd.DataFrame(data)
df


import pandas as pd

df = pd.read_csv('./datasets/weight-height.csv')
df


df.head()


df.head(10)


df.tail()


df.tail(10) # tail() method with an argument


df.columns

Index(['Gender', 'Height', 'Weight'], dtype='object')


df.shape

(10000, 3)


df.describe() # without any argument


df.describe(include='all', percentiles=[0.25, 0.5, 0.75, 0.85])


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   Gender  10000 non-null  object 
 1   Height  10000 non-null  float64
 2   Weight  10000 non-null  float64
dtypes: float64(2), object(1)
memory usage: 234.5+ KB


df.info(verbose=True)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   Gender  10000 non-null  object 
 1   Height  10000 non-null  float64
 2   Weight  10000 non-null  float64
dtypes: float64(2), object(1)
memory usage: 234.5+ KB


import pandas as pd
import numpy as np
data = [
    {"Name": "Asabeneh", "Country":"Finland","City":"Helsinki"},
    {"Name": "David", "Country":"UK","City":"London"},
    {"Name": "John", "Country":"Sweden","City":"Stockholm"},
    {"Name": "Eyob", "Country":"Finland","City":"Espoo"},
    {"Name": "Pawel", "Country":"Poland","City":"Warsaw"},
    {"Name": "Mahlet", "Country":"Ethiopia","City":"Addis Ababa"},
    {"Name": "Thomas", "Country":"Ethiopia","City":"Bahir Dar"},
    {"Name": "Lidiya", "Country":float('NaN'),"City":float('NaN')},
]
df = pd.DataFrame(data)
df


weights = [74, 78, 68, 108, 102, 58, 52, float('NaN')]
df['Weight'] = weights
df


heights = [173, 175, 169, 173, 195,168, 170, float('NaN')]
df['Height'] = heights
df


df['Height'] = df['Height'] * 0.01
df


# Using functions makes our code clean, but you can calculate the bmi without a function
def calculate_bmi ():
    weights = df['Weight']
    heights = df['Height']
    bmi = []
    for w,h in zip(weights, heights):
        b = w/(h*h)
        bmi.append(b)
    return bmi
    
bmi = calculate_bmi()


df['BMI'] = bmi
df


df['BMI'] = round(df['BMI'], 1)
df


df.head(25)


birth_year = ['1769', '1985', '1990', '1983', '1985','1995', '1999',float('NaN')]
df['Birth Year'] = birth_year
df['Current Year'] = 2021
df


df_copy = df.copy()
df_copy


# Let us imagine the Name column is not important.
# This does not affect the original data frame. To change from the original data frame we should add the inpplace argument
df.drop('Name', axis=1)


#The original dataframe has not beeen changes
df


# Let us imagine the Name column is not important.
# This does not affect the original data frame. To change from the original data frame we should add the inpplace argument
df.drop('Name', axis=1, inplace=True)
df


# We can also use the columns attribute to delete a column. Let us remove the country column
# To change the original we should make the inplace argument True
df.drop(columns = 'Country', axis=1)


#### Removing multiple columns
df.drop(['Country','City'], axis=1)


# To delete it from the original dataframe the inplace=True should be included
df.drop([7,5], axis = 0)

df


# To modifiy original dataframe the inplace=True should be included
df.rename(
    columns={
        "Country": "country",
        "City": "city",
        "Weight":"weight",
        "Height":"height",
        "BMI":'bmi',
        'Birth Year':'birth_year',
        'Current Year':'current_year'
    }
)


df.rename(columns = str.lower)

df


df.Weight.dtype

dtype('float64')


df['Birth Year'].dtype # it gives string object , we should change this to

dtype('O')


df.drop([7, 5], axis = 0, inplace=True)
df['Birth Year'] = df['Birth Year'].astype('int')

print(df['Birth Year'].dtype)

int32


df['Birth Year']

0    1769
1    1985
2    1990
3    1983
4    1985
6    1999
Name: Birth Year, dtype: int32


df['Current Year'] = df['Current Year'].astype('int')
df['Current Year'].dtype

dtype('int32')


ages = df['Current Year'] - df['Birth Year']
ages

0    252
1     36
2     31
3     38
4     36
6     22
dtype: int32


df['Birth Year']

0    1769
1    1985
2    1990
3    1983
4    1985
6    1999
Name: Birth Year, dtype: int32

df


df['Ages'] = ages

df


mean = (35 + 30) / 2
print('Mean: ',mean) #it is good to add some description to the output, so we know what is what

Mean:  32.5

df


df.iloc[0, 7] = (35 + 30) / 2

df


# Let's select the country column
df['Country']

0     Finland
1          UK
2      Sweden
3     Finland
4      Poland
6    Ethiopia
Name: Country, dtype: object


# let us select the city column
df['City']

0     Helsinki
1       London
2    Stockholm
3        Espoo
4       Warsaw
6    Bahir Dar
Name: City, dtype: object


# let us select Country and City columns
df[['Country','City']]


# let us select the height, weight, BMI, ages column
df[['Height','Weight','BMI','Ages']]


# people that were born before 1990
df[df['Birth Year'] < 1900]


# BMI if BMI is 18.5 to 25, it is a healthy weight 
df[df['BMI'] <= 25]


## Let's select peopel from Finland
df[df['Country'] =='Finland']


## Let's select people taller than 1.75 meter
df[df['Height'] > 1.7]


def classify_bmi(bmi):
    if bmi >= 30:
        return 'Obesity Range'
    elif bmi < 30 and bmi > 25:
        return 'Overweight Range'
    elif bmi < 25 and bmi >= 18.5:
        return 'Healthy Range'
    elif bmi < 18.5:
        return 'Underweight Range'


df['BMI class'] = df['BMI'].apply(lambda x: classify_bmi(x))

df


# Accessing only the first row
df.loc[0]

Country               Finland
City                 Helsinki
Weight                     74
Height                   1.73
BMI                      24.7
Birth Year               1769
Current Year             2021
Ages                     32.5
BMI class       Healthy Range
Name: 0, dtype: object


# Second row
df.loc[1]

Country                       UK
City                      London
Weight                        78
Height                      1.75
BMI                         25.5
Birth Year                  1985
Current Year                2021
Ages                          36
BMI class       Overweight Range
Name: 1, dtype: object


# Accessing the fifth column
df.iloc[4]

Country                   Poland
City                      Warsaw
Weight                       102
Height                      1.95
BMI                         26.8
Birth Year                  1985
Current Year                2021
Ages                          36
BMI class       Overweight Range
Name: 4, dtype: object


# Accessing the first and second row
df.loc[[0,1]]


# Accessing the first, third and fifth
df.loc[[0, 2, 4]]


data = [
    {"Name": "Asabeneh", "Country":"Finland","City":"Helsinki"},
    {"Name": "David", "Country":"UK","City":"London"},
    {"Name": "John", "Country":"Sweden","City":"Stockholm"},
    {"Name": "Eyob", "Country":"Finland","City":"Espoo"},
    {"Name": "Pawel", "Country":"Poland","City":"Warsaw"},
    {"Name": "Mahlet", "Country":"Ethiopia","City":"Addis Ababa"},
    {"Name": "Thomas", "Country":"Ethiopia","City":"Bahir Dar"},

]
df = pd.DataFrame(data, index = ['A','B','C','D','E','F','G'])

df


# Accessing a signle row that is named B
df.loc['A']

Name       Asabeneh
Country     Finland
City       Helsinki
Name: A, dtype: object


# Accessing a single row that is named B
df.loc['B']

Name        David
Country        UK
City       London
Name: B, dtype: object


df.loc[['A','B', 'E','G']]

df


# We can also access specific cell 

df.loc['A', 'Name']

'Asabeneh'


df.loc['C','Name']

'John'


df.loc['C','City']

'Stockholm'


# re-assigning the copied file, the df variable easy easy to write
df = df_copy
df['BMI class'] = df['BMI'].apply(lambda x : classify_bmi(x))


# first row

df.iloc[0]

Name                 Asabeneh
Country               Finland
City                 Helsinki
Weight                     74
Height                   1.73
BMI                      24.7
Birth Year               1769
Current Year             2021
BMI class       Healthy Range
Name: 0, dtype: object


df.iloc[[0]]


# second row
df.iloc[1]

Name                       David
Country                       UK
City                      London
Weight                        78
Height                      1.75
BMI                         25.5
Birth Year                  1985
Current Year                2021
BMI class       Overweight Range
Name: 1, dtype: object


df.iloc[[1]]


# some selected rows
df.iloc[[0, 2, 4]]


# display all the data
df.iloc[:]


# slicing the first second row
df.iloc[0:2]

df


# Boolean indexing
df.iloc[lambda x : x.index % 2 == 0]


# Boolean indexing
df.iloc[lambda x : x.index % 2 != 0]


# index and column ,[index, col] to get a value in a cell

df.iloc[0, 1]

'Finland'

df


# slicing three rows
df.iloc[0:3]


## Slicing some part of a data frame
df.iloc[0:3,0:3]


## Slicing some part of a data frame
df.iloc[0:3,3:]

df


joined_df = pd.concat([df, df])
joined_df

df


# the info provides information about the data
# Only the Name and Current Year columns are complete data values
# The last row has many NaN value, we can fill it with some value
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8 entries, 0 to 7
Data columns (total 9 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   Name          8 non-null      object 
 1   Country       7 non-null      object 
 2   City          7 non-null      object 
 3   Weight        7 non-null      float64
 4   Height        7 non-null      float64
 5   BMI           7 non-null      float64
 6   Birth Year    7 non-null      object 
 7   Current Year  8 non-null      int64  
 8   BMI class     7 non-null      object 
dtypes: float64(3), int64(1), object(5)
memory usage: 704.0+ bytes


# to modify it from the originial we should use inplace=True argument
df.fillna('sample data')


# We can also replace only a certain columns
df['Country'].fillna('Finland', inplace=True)
df


# We can also remove the row containing the null
# We can use inplace=True, to make change to the original

df.dropna()


# We can use mean, median, mode methods to calculate descriptive statistics from data using pandas
mean = df.iloc[1:]['Birth Year'].astype(float).mean()


# Replacing outliers
# Birth year 1769 does sould plausible, lets replace or imput that vaue with avarage birth year
# To target 1769 data we can use loc or iloc method
df.loc[0, 'Birth Year']

'1769'


df.iloc[0, 6]

'1769'


df.iloc[0, 6] = round( mean)
df


joined_df


joined_df.duplicated()

0    False
1    False
2    False
3    False
4    False
5    False
6    False
7    False
0     True
1     True
2     True
3     True
4     True
5     True
6     True
7     True
dtype: bool


# removing dupliacates
joined_df.drop_duplicates(inplace=True)
joined_df


## Lets drop the null and do descriptive statistics
joined_df.dropna(inplace=True)
joined_df


joined_df.describe()


# We can also use mean, median mode separately

joined_df.mean()

Weight          7.714286e+01
Height          1.747143e+00
BMI             2.505714e+01
Birth Year      2.527426e+26
Current Year    2.021000e+03
dtype: float64


joined_df.median()

Weight            74.00
Height             1.73
BMI               24.70
Birth Year      1985.00
Current Year    2021.00
dtype: float64


# mode of the Country column
joined_df['Country'].mode()

0    Ethiopia
1     Finland
dtype: object


# Standard Deviation of the numeric columns
joined_df.std()

Weight          21.066787
Height           0.092864
BMI              5.736682
Current Year     0.000000
dtype: float64


# Varience of the numeric columns
joined_df.var()

Weight          443.809524
Height            0.008624
BMI              32.909524
Current Year      0.000000
dtype: float64


# Correlation shows the relationship between two variables. The value is between -1 and 1. 
# 0 No correlation at all 
# 1 mean a perfect relation
# BMI has high correlation with Weight, however Height has relatively low correlation with BMI
joined_df.corr()


joined_df['Country'].value_counts()

Ethiopia    2
Finland     2
UK          1
Sweden      1
Poland      1
Name: Country, dtype: int64


joined_df['City'].value_counts()

Addis Ababa    1
Helsinki       1
Espoo          1
Bahir Dar      1
Stockholm      1
Warsaw         1
London         1
Name: City, dtype: int64


df.groupby('Country').mean()


df.groupby('Country', sort=True).mean()


df.sort_values('Country')


df.sort_values('Country' , ascending=False)


df.sort_values('City' , ascending=False, na_position='first')


df.sort_values('BMI class', key=lambda col: col.str.lower())


import matplotlib.pyplot as plt


joined_df.plot()
plt.show()


joined_df[['Weight','Height','BMI']]


joined_df[['Weight','Height','BMI']].plot()
plt.show()


joined_df[['Height','BMI']].plot(kind='scatter', x='Height', y = 'BMI', title = 'Height vs BMI')
plt.show()


joined_df[['Weight','BMI']].plot(kind='scatter', x='Weight', y = 'BMI', title = 'Weight vs BMI')
plt.show()


joined_df[['Weight']].plot(kind='bar')
plt.show()


joined_df[['Weight']].plot(kind='hist')
plt.show()


 # Let's read a datas set and modify the height and weight value


df = pd.read_csv('./datasets/weight-height.csv')


df.head()


df.tail()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10000 entries, 0 to 9999
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   Gender  10000 non-null  object 
 1   Height  10000 non-null  float64
 2   Weight  10000 non-null  float64
dtypes: float64(2), object(1)
memory usage: 234.5+ KB


df.shape

(10000, 3)


df.columns

Index(['Gender', 'Height', 'Weight'], dtype='object')


# changing inch to centimenter
# pounds to killogram
df['Height in Cm'] = df['Height'].apply(lambda x : x * 2.54 )
df['Weight in Kg'] = df['Weight'].apply(lambda x : x * 0.453592 )


df['BMI']  = df['Weight in Kg'] / (df['Height in Cm'] * 0.01) ** 2


df.head()


df.describe()


df.corr()


x = df['Height in Cm']
y = df['Weight in Kg']


m, b = np.polyfit(x, y, 1)

df[['Height in Cm', 'Weight in Kg']].plot(kind='scatter', x = 'Height in Cm', y='Weight in Kg', title='Height Versus Weight')
plt.plot(x, m*x + b, c='r', linewidth=5)
plt.show()

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801
...	...	...	...
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801

	Gender	Height	Weight
0	Male	73.847017	241.893563
1	Male	68.781904	162.310473
2	Male	74.110105	212.740856
3	Male	71.730978	220.042470
4	Male	69.881796	206.349801
5	Male	67.253016	152.212156
6	Male	68.785081	183.927889
7	Male	68.348516	167.971110
8	Male	67.018950	175.929440
9	Male	63.456494	156.399676

	Gender	Height	Weight
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

	Gender	Height	Weight
9990	Female	63.179498	141.266100
9991	Female	62.636675	102.853563
9992	Female	62.077832	138.691680
9993	Female	60.030434	97.687432
9994	Female	59.098250	110.529686
9995	Female	66.172652	136.777454
9996	Female	67.067155	170.867906
9997	Female	63.867992	128.475319
9998	Female	69.034243	163.852461
9999	Female	61.944246	113.649103

	Height	Weight
count	10000.000000	10000.000000
mean	66.367560	161.440357
std	3.847528	32.108439
min	54.263133	64.700127
25%	63.505620	135.818051
50%	66.318070	161.212928
75%	69.174262	187.169525
max	78.998742	269.989699

	Gender	Height	Weight
count	10000	10000.000000	10000.000000
unique	2	NaN	NaN
top	Female	NaN	NaN
freq	5000	NaN	NaN
mean	NaN	66.367560	161.440357
std	NaN	3.847528	32.108439
min	NaN	54.263133	64.700127
25%	NaN	63.505620	135.818051
50%	NaN	66.318070	161.212928
75%	NaN	69.174262	187.169525
85%	NaN	70.577106	197.536443
max	NaN	78.998742	269.989699

	Name	Country	City
0	Asabeneh	Finland	Helsinki
1	David	UK	London
2	John	Sweden	Stockholm
3	Eyob	Finland	Espoo
4	Pawel	Poland	Warsaw
5	Mahlet	Ethiopia	Addis Ababa
6	Thomas	Ethiopia	Bahir Dar
7	Lidiya	NaN	NaN

	Country	City	Weight	Height	BMI	Birth Year	Current Year
0	Finland	Helsinki	74.0	1.73	24.7	1769	2021
1	UK	London	78.0	1.75	25.5	1985	2021
2	Sweden	Stockholm	68.0	1.69	23.8	1990	2021
3	Finland	Espoo	108.0	1.73	36.1	1983	2021
4	Poland	Warsaw	102.0	1.95	26.8	1985	2021
5	Ethiopia	Addis Ababa	58.0	1.68	20.5	1995	2021
6	Ethiopia	Bahir Dar	52.0	1.70	18.0	1999	2021
7	NaN	NaN	NaN	NaN	NaN	NaN	2021

	Weight	Height	BMI	Current Year
count	7.000000	7.000000	7.000000	7.0
mean	77.142857	1.747143	25.057143	2021.0
std	21.066787	0.092864	5.736682	0.0
min	52.000000	1.680000	18.000000	2021.0
25%	63.000000	1.695000	22.150000	2021.0
50%	74.000000	1.730000	24.700000	2021.0
75%	90.000000	1.740000	26.150000	2021.0
max	108.000000	1.950000	36.100000	2021.0

	Weight	Height	BMI	Current Year
Weight	1.000000	0.644298	0.912597	NaN
Height	0.644298	1.000000	0.275980	NaN
BMI	0.912597	0.275980	1.000000	NaN
Current Year	NaN	NaN	NaN	NaN

	Weight	Height	BMI	Current Year
Country
Ethiopia	55.0	1.69	19.25	2021
Finland	91.0	1.73	30.40	2021
Poland	102.0	1.95	26.80	2021
Sweden	68.0	1.69	23.80	2021
UK	78.0	1.75	25.50	2021

	Height	Weight	Height in Cm	Weight in Kg	BMI
Height	1.000000	0.924756	1.000000	0.924756	0.669199
Weight	0.924756	1.000000	0.924756	1.000000	0.896438
Height in Cm	1.000000	0.924756	1.000000	0.924756	0.669199
Weight in Kg	0.924756	1.000000	0.924756	1.000000	0.896438
BMI	0.669199	0.896438	0.669199	0.896438	1.000000

Pandas¶

Installing Pandas¶

Pandas Series and DataFrames¶

Pandas Series¶

Importing Pandas¶

Creating Pandas Series from list¶

Getting the index from the Pandas Series¶

Creating Pandas Series with custom index¶

Creating Pandas Series from a Dictionary¶

Creating a Constant Pandas Series¶

Creating a Pandas Series Using Linspace¶

Accessing specific item from Pandas Series¶

Copying a Panda Series with copy method¶

DataFrames¶

Creating DataFrames from List of Lists¶

Creating DataFrame Using Dictionary¶

Creating DataFrames from a List of Dictionaries¶

Reading different file formats Using Pandas¶

Reading CSV File Using Pandas¶

Loading a CSV file¶

Data Exploration¶

Reading the first few records of a dataset using head()¶

Reading the last records of a dataset¶

Number of Columns¶

DataFrame shape¶

Descriptive Statistics¶

Get information about the dataset¶

Modifying a DataFrame¶

Creating a DataFrame¶

Adding a New Column¶

Modifying column values¶

Formating DataFrame columns¶

Copying Dataframe¶

Deleting a DataFrame Column¶

Deleting Columns¶

Deleting Rows¶

Renaming Columns¶

Checking data types of Column values¶

Selecting Column(s)¶

Boolean Indexing¶

Using apply method to modify pandas data frame¶

Accessing row(s) using loc attribute¶

Accessing a single row¶

Accessing Multiple Rows¶

Name indexes Pandas DataFrame¶

Accessing DataFrame values using iloc method¶

Concating DataFrames¶

Cleaning Data¶

Dropping null value¶

Imputation¶

Removing Duplicates¶

Using descriptive Statistics methods¶

Use value_counts method¶

Using groupby method to group columns¶

Visulization by plotting data¶

Cleaning Data¶

Exercises¶