Pandas Course notebook

In [ ]:

!pip install pandas

!pip install pandas

In [ ]:

import pandas as pd
import numpy as np

dataset1=[1, 3, 5, np.nan, 6, 8]
df1=pd.Series(dataset1)
df1

import pandas as pd import numpy as np dataset1=[1, 3, 5, np.nan, 6, 8] df1=pd.Series(dataset1) df1

Out[ ]:

0    1.0
1    3.0
2    5.0
3    NaN
4    6.0
5    8.0
dtype: float64

In [ ]:

import pandas as pd
dataset1=[1, 3, 5, np.nan, 6, 8]
df1=pd.Series(dataset1, index=["a","b","c","e","f","g"])
print (df1)

import pandas as pd dataset1=[1, 3, 5, np.nan, 6, 8] df1=pd.Series(dataset1, index=["a","b","c","e","f","g"]) print (df1)

a    1.0
b    3.0
c    5.0
e    NaN
f    6.0
g    8.0
dtype: float64

In [ ]:

print (df1["a"])

print (df1["a"])

1.0

In [ ]:

import pandas as pd
dataset1={"Vehicle number":1, "Wheels":4, "Doors":4}
df1=pd.Series(dataset1)
print (df1)

import pandas as pd dataset1={"Vehicle number":1, "Wheels":4, "Doors":4} df1=pd.Series(dataset1) print (df1)

Vehicle number    1
Wheels            4
Doors             4
dtype: int64

In [ ]:

data = {'name': ['Alice', 'Bob', 'Charlie', 'David'],
        'age': [25, 32, 18, 47],
        'gender': ['F', 'M', 'M', 'M']}
df = pd.DataFrame(data)
print(df)

data = {'name': ['Alice', 'Bob', 'Charlie', 'David'], 'age': [25, 32, 18, 47], 'gender': ['F', 'M', 'M', 'M']} df = pd.DataFrame(data) print(df)

      name  age gender
0    Alice   25      F
1      Bob   32      M
2  Charlie   18      M
3    David   47      M

In [ ]:

import pandas as pd
dataset1={"Vehicle number":[1,2,3], "Wheels":[4,2,4], "Doors":[4,0,5]}
df1=pd.DataFrame(dataset1, index=["Car","Motorcycle","Van"])
print(df1)

import pandas as pd dataset1={"Vehicle number":[1,2,3], "Wheels":[4,2,4], "Doors":[4,0,5]} df1=pd.DataFrame(dataset1, index=["Car","Motorcycle","Van"]) print(df1)

            Vehicle number  Wheels  Doors
Car                      1       4      4
Motorcycle               2       2      0
Van                      3       4      5

In [ ]:

print (df1.loc["Car"])

print (df1.loc["Car"])

Vehicle number    1
Wheels            4
Doors             4
Name: Car, dtype: int64

In [ ]:

import pandas as pd

## Importing a CSV file
df = pd.read_csv('data.csv')
df

import pandas as pd ## Importing a CSV file df = pd.read_csv('data.csv') df

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

169 rows × 4 columns

In [ ]:

## Export a CSV file
df.to_csv('data.csv', index=False)#The index=False argument tells Pandas not to write the row index to the CSV file.

## Export a CSV file df.to_csv('data.csv', index=False)#The index=False argument tells Pandas not to write the row index to the CSV file.

In [ ]:

df.head()

df.head()

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0

In [ ]:

df.tail()

df.tail()

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

In [ ]:

df.info()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 169 entries, 0 to 168
Data columns (total 4 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   Duration  169 non-null    int64  
 1   Pulse     169 non-null    int64  
 2   Maxpulse  169 non-null    int64  
 3   Calories  164 non-null    float64
dtypes: float64(1), int64(3)
memory usage: 5.4 KB

In [ ]:

df.isnull().value_counts()

df.isnull().value_counts()

Out[ ]:

Duration  Pulse  Maxpulse  Calories
False     False  False     False       164
                           True          5
dtype: int64

In [ ]:

df.dropna(inplace=True)
df

df.dropna(inplace=True) df

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

164 rows × 4 columns

In [ ]:

df.isnull().value_counts()

df.isnull().value_counts()

Out[ ]:

Duration  Pulse  Maxpulse  Calories
False     False  False     False       164
dtype: int64

In [ ]:

import pandas as pd
df=pd.read_csv("data.csv")
df.fillna(130, inplace=True)
df["Calories"].fillna(130, inplace=True)
df

import pandas as pd df=pd.read_csv("data.csv") df.fillna(130, inplace=True) df["Calories"].fillna(130, inplace=True) df

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

169 rows × 4 columns

In [ ]:

df.isnull().value_counts()

df.isnull().value_counts()

Out[ ]:

Duration  Pulse  Maxpulse  Calories
False     False  False     False       169
dtype: int64

In [ ]:

import pandas as pd

df=pd.read_csv("data.csv")

meancal=df["Calories"].mean()
mediancal=df["Calories"].median()
modecal=df["Calories"].mode()

print ("The mean of calories is " + str(meancal) + " The median of calories is " + str(mediancal) + " The mode of calories is " + str(modecal)) 

meandf=df["Calories"].fillna(meancal)
mediandf=df["Calories"].fillna(mediancal)
modedf=df["Calories"].fillna(modecal)

import pandas as pd df=pd.read_csv("data.csv") meancal=df["Calories"].mean() mediancal=df["Calories"].median() modecal=df["Calories"].mode() print ("The mean of calories is " + str(meancal) + " The median of calories is " + str(mediancal) + " The mode of calories is " + str(modecal)) meandf=df["Calories"].fillna(meancal) mediandf=df["Calories"].fillna(mediancal) modedf=df["Calories"].fillna(modecal)

The mean of calories is375.79024390243904 The median of calories is 318.6 The mode of calories is 0    300.0
dtype: float64

In [ ]:

meandf

meandf

Out[ ]:

0      409.1
1      479.0
2      340.0
3      282.4
4      406.0
       ...  
164    290.8
165    300.0
166    310.2
167    320.4
168    330.4
Name: Calories, Length: 169, dtype: float64

In [ ]:

mediandf

mediandf

Out[ ]:

0      409.1
1      479.0
2      340.0
3      282.4
4      406.0
       ...  
164    290.8
165    300.0
166    310.2
167    320.4
168    330.4
Name: Calories, Length: 169, dtype: float64

In [ ]:

modedf

modedf

Out[ ]:

0      409.1
1      479.0
2      340.0
3      282.4
4      406.0
       ...  
164    290.8
165    300.0
166    310.2
167    320.4
168    330.4
Name: Calories, Length: 169, dtype: float64

In [ ]:

import pandas as pd 

df1=pd.read_csv("data.csv")
df2=pd.read_csv("data.csv")

						
for x in df1.index: #replace all values in duration above 120 with 120 
	if df1.loc[x, "Duration"] > 120:
		df1.loc[x,"Duration"] = 120

for y in df2.index: #drop all values above 120
	if df2.loc[y, "Duration"] >120:
		df2.drop(y, inplace = True)

import pandas as pd df1=pd.read_csv("data.csv") df2=pd.read_csv("data.csv") for x in df1.index: #replace all values in duration above 120 with 120 if df1.loc[x, "Duration"] > 120: df1.loc[x,"Duration"] = 120 for y in df2.index: #drop all values above 120 if df2.loc[y, "Duration"] >120: df2.drop(y, inplace = True)

In [ ]:

df1

df1

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

169 rows × 4 columns

In [ ]:

df2

df2

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

156 rows × 4 columns

In [ ]:

import pandas as pd

df1=pd.read_csv("data.csv")
						
df1.duplicated().value_counts() #search for duplicates and output true when found

import pandas as pd df1=pd.read_csv("data.csv") df1.duplicated().value_counts() #search for duplicates and output true when found

Out[ ]:

False    162
True       7
dtype: int64

In [ ]:

df1.drop_duplicates(inplace = True) #drop all duplicates

df1 #find and drop duplicates example

df1.drop_duplicates(inplace = True) #drop all duplicates df1 #find and drop duplicates example

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
0	60	110	130	409.1
1	60	117	145	479.0
2	60	103	135	340.0
3	45	109	175	282.4
4	45	117	148	406.0
...	...	...	...	...
164	60	105	140	290.8
165	60	110	145	300.0
166	60	115	145	310.2
167	75	120	150	320.4
168	75	125	150	330.4

162 rows × 4 columns

In [ ]:

df1 = pd.DataFrame({'id': [1, 2, 3, 4], 'name': ['Alice', 'Bob', 'Charlie', 'David']})
df2 = pd.DataFrame({'id': [1, 2, 3, 4], 'age': [25, 32, 18, 47]})

df1 = pd.DataFrame({'id': [1, 2, 3, 4], 'name': ['Alice', 'Bob', 'Charlie', 'David']}) df2 = pd.DataFrame({'id': [1, 2, 3, 4], 'age': [25, 32, 18, 47]})

In [ ]:

df1

df1

Out[ ]:

	id	name
0	1	Alice
1	2	Bob
2	3	Charlie
3	4	David

In [ ]:

df2

df2

Out[ ]:

	id	age
0	1	25
1	2	32
2	3	18
3	4	47

In [ ]:

merged_df = pd.merge(df1, df2, on='id')  # Merge DataFrames on 'id' column
merged_df

merged_df = pd.merge(df1, df2, on='id') # Merge DataFrames on 'id' column merged_df

Out[ ]:

	id	name	age
0	1	Alice	25
1	2	Bob	32
2	3	Charlie	18
3	4	David	47

In [ ]:

df1 = pd.DataFrame({'id': [1, 2, 3, 4], 'name': ['Alice', 'Bob', 'Charlie', 'David']})
df2 = pd.DataFrame({'id': [1, 2, 3, 4], 'age': [25, 32, 18, 47]})

df1

df1 = pd.DataFrame({'id': [1, 2, 3, 4], 'name': ['Alice', 'Bob', 'Charlie', 'David']}) df2 = pd.DataFrame({'id': [1, 2, 3, 4], 'age': [25, 32, 18, 47]}) df1

Out[ ]:

	id	name
0	1	Alice
1	2	Bob
2	3	Charlie
3	4	David

In [ ]:

df2

df2

Out[ ]:

	id	age
0	1	25
1	2	32
2	3	18
3	4	47

In [ ]:

joined_df = df1.set_index('id').join(df2.set_index('id'))  # Join DataFrames on 'id' column
joined_df

joined_df = df1.set_index('id').join(df2.set_index('id')) # Join DataFrames on 'id' column joined_df

Out[ ]:

	name	age
id
1	Alice	25
2	Bob	32
3	Charlie	18
4	David	47

In [ ]:

In [ ]:

import pandas as pd
df1=pd.read_csv("data.csv") 
df1.describe()

import pandas as pd df1=pd.read_csv("data.csv") df1.describe()

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
count	169.000000	169.000000	169.000000	164.000000
mean	63.846154	107.461538	134.047337	375.790244
std	42.299949	14.510259	16.450434	266.379919
min	15.000000	80.000000	100.000000	50.300000
25%	45.000000	100.000000	124.000000	250.925000
50%	60.000000	105.000000	131.000000	318.600000
75%	60.000000	111.000000	141.000000	387.600000
max	300.000000	159.000000	184.000000	1860.400000

In [ ]:

df1.corr()

df1.corr()

Out[ ]:

	Duration	Pulse	Maxpulse	Calories
Duration	1.000000	-0.155408	0.009403	0.922717
Pulse	-0.155408	1.000000	0.786535	0.025121
Maxpulse	0.009403	0.786535	1.000000	0.203813
Calories	0.922717	0.025121	0.203813	1.000000

In [ ]: