In [1]: #_______________________________________FDS(Assignment No-1)______________________________
# Q-1) Write a Python program to create a dataframe containing columns name,
# age and percentage. Add 10 rows to the dataframe. View the dataframe.
import pandas as pd
df=pd.DataFrame(columns=['Name','Age','Percentage'])
df.loc[0]=['Rohit',20,74]
df.loc[1]=['Rohan',20,84]
df.loc[2]=['Ram',21,94]
df.loc[3]=['Rakesh',21,77]
df.loc[4]=['om',20,66]
df.loc[5]=['yash',20,70]
df.loc[6]=['saurabh',21,84]
df.loc[7]=['akash',20,94]
df.loc[8]=['Ronney',20,84]
df.loc[9]=['Rahul',20,94]
df
Out[1]: Name Age Percentage
0 Rohit 20 74
1 Rohan 20 84
2 Ram 21 94
3 Rakesh 21 77
4 om 20 66
5 yash 20 70
6 saurabh 21 84
7 akash 20 94
8 Ronney 20 84
9 Rahul 20 94
In [4]: # Q-2) Write a Python program to print the shape, number of rows-columns,
# data types, feature names and the description of the data
import pandas as pd
df=pd.DataFrame(columns=['Name','Age','Percentage'])
df.loc[0]=['Rohit',20,74]
df.loc[1]=['Rohan',20,84]
df.loc[2]=['Ram',21,94]
df.loc[3]=['Rakesh',21,77]
df.loc[4]=['om',20,66]
df.loc[5]=['yash',20,70]
df.loc[6]=['saurabh',21,84]
df.loc[7]=['akash',20,94]
df.loc[8]=['Ronney',20,84]
df.loc[9]=['Rahul',20,94]
df
s=df.shape
print("shape: ",s)
c=len(df.columns)
print("No.of columns: ",c)
r=len(df)
print("No.of rows: ",r)
df.dtypes
fname=pd.get_dummies(df)
print(fname)
df.describe()
shape: (10, 3)
No.of columns: 3
No.of rows: 10
Age Percentage Name_Rahul Name_Rakesh Name_Ram Name_Rohan Name_Rohit
0 20 74 False False False False True \
1 20 84 False False False True False
2 21 94 False False True False False
3 21 77 False True False False False
4 20 66 False False False False False
5 20 70 False False False False False
6 21 84 False False False False False
7 20 94 False False False False False
8 20 84 False False False False False
9 20 94 True False False False False
Name_Ronney Name_akash Name_om Name_saurabh Name_yash
0 False False False False False
1 False False False False False
2 False False False False False
3 False False False False False
4 False False True False False
5 False False False False True
6 False False False True False
7 False True False False False
8 True False False False False
9 False False False False False
Out[4]: Age Percentage
count 10.000000 10.000000
mean 20.300000 82.100000
std 0.483046 10.181137
min 20.000000 66.000000
25% 20.000000 74.750000
50% 20.000000 84.000000
75% 20.750000 91.500000
max 21.000000 94.000000
In [5]: # Q-3) Write a Python program to view basic statistical details of the data.
import pandas as pd
import numpy as np
dict={"rno":['1','2','3','4'],"marks":['80','90','60','70']}
df=pd.DataFrame(dict)
df.astype(float).describe()
Out[5]: rno marks
count 4.000000 4.000000
mean 2.500000 75.000000
std 1.290994 12.909944
min 1.000000 60.000000
25% 1.750000 67.500000
50% 2.500000 75.000000
75% 3.250000 82.500000
max 4.000000 90.000000
In [1]: # Q-4) Write a Python program to Add 5 rows with duplicate values and
# missing values. Add a column ‘remarks’ with empty values.
# Display the data.
import pandas as pd
df=pd.DataFrame(columns=['Name','Age','Percentage'])
df.loc[0]=['Rohit',20,74]
df.loc[1]=['Rohan',20,84]
df.loc[2]=['Ram',21,94]
df.loc[3]=['Rakesh',21,77]
df.loc[4]=['om',20,66]
df.loc[5]=['yash',20,70]
df.loc[6]=['saurabh',21,84]
df.loc[7]=['akash',20,94]
df.loc[8]=['Ronney',20,84]
df.loc[9]=['Rahul',20,94]
df.loc[10]=[None,None,None]
df.loc[11]=['saurabh',21,84]
df.loc[12]=[None,None,None]
df.loc[13]=['Ronney',20,84]
df.loc[14]=['Rahul',20,94]
df.loc[15]=[None,None,None]
df["remarks"]=None
df
Out[1]: Name Age Percentage remarks
0 Rohit 20 74 None
1 Rohan 20 84 None
2 Ram 21 94 None
3 Rakesh 21 77 None
4 om 20 66 None
5 yash 20 70 None
6 saurabh 21 84 None
7 akash 20 94 None
8 Ronney 20 84 None
9 Rahul 20 94 None
10 None None None None
11 saurabh 21 84 None
12 None None None None
13 Ronney 20 84 None
14 Rahul 20 94 None
15 None None None None
In [2]: # Q-5) Write a Python program to get the number of observations, missing values
# and duplicate values.
import pandas as pd
df=pd.DataFrame(columns=['Name','Age','Percentage'])
df.loc[0]=['Rohit',20,74]
df.loc[1]=['Rohan',20,84]
df.loc[2]=['Ram',21,94]
df.loc[3]=['Rakesh',21,77]
df.loc[4]=['om',20,66]
df.loc[5]=['yash',20,70]
df.loc[6]=['saurabh',21,84]
df.loc[7]=['akash',20,94]
df.loc[8]=['Ronney',20,84]
df.loc[9]=['Rahul',20,94]
df.loc[10]=[None,None,None]
df.loc[11]=['saurabh',21,84]
df.loc[12]=[None,None,None]
df.loc[13]=['Ronney',20,84]
df.loc[14]=['Rahul',20,94]
df.loc[15]=[None,None,None]
obs=df.info()
print("No.of observations: ",obs)
duplicate=df.duplicated()
print("Duplicated Values: ",duplicate)
miss=df[df.isnull()]
print("Missing values: ",miss)
<class 'pandas.core.frame.DataFrame'>
Index: 16 entries, 0 to 15
Data columns (total 3 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Name 13 non-null object
1 Age 13 non-null object
2 Percentage 13 non-null object
dtypes: object(3)
memory usage: 512.0+ bytes
No.of observations: None
Duplicated Values: 0 False
1 False
2 False
3 False
4 False
5 False
6 False
7 False
8 False
9 False
10 False
11 True
12 True
13 True
14 True
15 True
dtype: bool
Missing values: Name Age Percentage
0 NaN NaN NaN
1 NaN NaN NaN
2 NaN NaN NaN
3 NaN NaN NaN
4 NaN NaN NaN
5 NaN NaN NaN
6 NaN NaN NaN
7 NaN NaN NaN
8 NaN NaN NaN
9 NaN NaN NaN
10 None None None
11 NaN NaN NaN
12 None None None
13 NaN NaN NaN
14 NaN NaN NaN
15 None None None
In [6]: # Q-6) Write a Python program to drop ‘remarks’ column from the dataframe.
# Also drop all null and empty values.
# Print the modified data.
import pandas as pd
df=pd.DataFrame(columns=['Name','Age','Percentage'])
df.loc[0]=['Rohit',20,74]
df.loc[1]=['Rohan',20,84]
df.loc[2]=['Ram',21,94]
df.loc[3]=['Rakesh',21,77]
df.loc[4]=['om',20,66]
df.loc[5]=['yash',20,70]
df.loc[6]=['saurabh',21,84]
df.loc[7]=['akash',20,94]
df.loc[8]=['Ronney',20,84]
df.loc[9]=['Rahul',20,94]
df.loc[10]=[None,None,None]
df.loc[11]=['saurabh',21,84]
df.loc[12]=[None,None,None]
df.loc[13]=['Ronney',20,84]
df.loc[14]=['Rahul',20,94]
df.loc[15]=[None,None,None]
df["remarks"]=None
df
df.drop(columns='remarks',axis=1,inplace=True)
df
Out[6]: Name Age Percentage
0 Rohit 20 74
1 Rohan 20 84
2 Ram 21 94
3 Rakesh 21 77
4 om 20 66
5 yash 20 70
6 saurabh 21 84
7 akash 20 94
8 Ronney 20 84
9 Rahul 20 94
10 None None None
11 saurabh 21 84
12 None None None
13 Ronney 20 84
14 Rahul 20 94
15 None None None
In [7]: # Q-7) Write a Python program to generate a line plot of name vs percentage.
import matplotlib.pyplot as plt
name=['Rohit','Rahul','Rohan','Rakesh','Ram']
percentage=[80,78,89,79,88]
plt.plot(name,percentage)
plt.title("Line Graph")
plt.xlabel("Name")
plt.ylabel("Pecentage")
plt.show()
In [8]: # Q-8) Write a Python program to generate a scatter plot of name vs percentage
import matplotlib.pyplot as plt
name=['Rohit','Rohan','Rahul','Ram','Rakesh']
percentage=[78,80,90,67,88]
plt.scatter(name,percentage)
plt.title("Scatter Graph")
plt.xlabel("Name")
plt.ylabel("Percentage")
plt.show()
In [ ]:
