1)
a) import pandas as pd
# initialize data of lists.
Grade = {'Name': ['Rashmi', 'Harsh', 'Ganesh', 'Priya',’Vivek’,’Anita’,’Kartik’],
'Grade': [‘A1’, ‘A2’, ‘B1’, ‘A1’, ‘B2’, ‘A2’, ‘A1’,]}
# Create DataFrame
Gr = pd.DataFrame(Grade)
b) # Insert New Column into the DataFrame
new_column_data = {'Percentage': [92, 89, None, 95, 68, None, 93]
new_columns_df = pd.DataFrame(new_column_data)
Gr = pd.DataFrame(new_column_df)
c) # Reordering columns using iloc
df_reordered = df.iloc[:, [0, 2, 1]] # 'Name', 'Percentage', 'Grade'
d) # Drop column 'C'
df = data.drop('C', axis=1)
e) update_df = df.drop(['c', 'd'])
2)
6)
d={'Eno':[1,2,3],'Ename':['Ritesh','Aakash','Manu'],'Salary':[15000,16000,18000]}
df=pd.DataFrame(d)
print(df)
sum1=0
for i in range(len(df)):
sum1=sum1+df.loc[i,'Salary']
print(sum1)
7)
import pandas as pd
data={
‘Name’:[“Seema”,”Nikshav”,”Rajni”],
‘Age’:[36,40,39],
‘Designation’:[“Manager”,”Clerk”,”Accountant”]
}
df=pd.DataFrame(data)
df.sort_values(by=”Age”,ascending=True)
print(df)
8)
Import pandas as pd
salesDict={
‘item’:[“A”, “B”, “C”, “D”, “E”, “F”],
‘sales’:[10,12,50,10,5,90]
}
Sales = pd.DataFrame(salesDict)
Print(sales.item[4])
9)
EMP.insert(loc=3,column=”Sal”,value=Sal)
10)
import pandas as pd
data = [
['S101', 'Amy', 70],
['S102', 'Bandhi', 69],
['S104', 'Cathy', 75],
['S105', 'Gundaho', 82]
]
columns = ['ID', 'Name', 'Score']
df = pd.DataFrame(data, columns=columns)
print(df)
11)
import pandas as pd
df = pd.DataFrame([[1, 2], [3, 4]], columns = ['a','b'])
12)
1) WAP to display the shape of employee.csv file.
Code:
import pandas as pd
data = pd.read_csv("path-of-file.csv")
print("shape of employee.csv file: ")
print(csvData.shape)
Output:
shape of employee.csv file:
(8, 5)
2. WAP to display Name, Age and Salary from employee.csv
Code:
import pandas as pd
data= pd.read_csv("path-of-file.csv",usecols=["Name","Age","Salary"])
print(data)
Output:
Name Age Salary
0 Ritesh 25.0 15000.0
1 Akash 26.0 16000.0
2 NaN NaN NaN
3 Mahima 27.0 20000.0
4 Lakshay 28.0 18000.0
5 Manu 25.0 25000.0
6 Nidhi 26.0 NaN
7 Geetu 30.0 28000.0
3. WAP to display only 5 records from employee.csv.
Code:
import pandas as pd
data= pd.read_csv("path-of-file.csv")
print(data.head(5))
Output:
empid Name Age City Salary
0 100.0 Ritesh 25.0 mumbai 15000.0
1 101.0 Akash 26.0 Goa 16000.0
2 NaN NaN NaN NaN NaN
3 102.0 Mahima 27.0 Hyderabad 20000.0
4 103.0 Lakshay 28.0 Delhi 18000.0
4. WAP to display records without header.
Code:
import pandas as pd
data = pd.read_csv("path-of-file.csv", header=None)
print(data)
Output:
0 1 2 3 4
0 empid Name Age City Salary
1 100 Ritesh 25 mumbai 15000
2 101 Akash 26 Goa 16000
3 NaN NaN NaN NaN NaN
4 102 Mahima 27 Hyderabad 20000
5 103 Lakshay 28 Delhi 18000
6 104 Manu 25 Mumbai 25000
7 105 Nidhi 26 Delhi NaN
8 106 Geetu 30 Bangaluru 28000
5. WAP to display employee.csv file without index numbers.
Code:
import pandas as pd
data = pd.read_csv("path-of-file.csv")
print(data.to_string(index=False))
Output:
empid Name Age City Salary
100.0 Ritesh 25.0 mumbai 15000.0
101.0 Akash 26.0 Goa 16000.0
NaN NaN NaN NaN NaN
102.0 Mahima 27.0 Hyderabad 20000.0
103.0 Lakshay 28.0 Delhi 18000.0
104.0 Manu 25.0 Mumbai 25000.0
105.0 Nidhi 26.0 Delhi NaN
106.0 Geetu 30.0 Bangaluru 28000.0
6. WAP to display employee.csv file with new column names.
import pandas as pd
data = pd.read_csv("path-of-file.csv", names=["a","b","c","d","e"])
print(data)
7. WAP to modify the employee name from Mahima to Harsh.
import pandas as pd
data = pd.read_csv("path-of-file.csv")
df = pd.DataFrame(data)
df["Name"] = df["Name"].replace("Mahima", "Harsh")
print(df)
8. WAP to create a new CSV file by copying the contents of employee.csv.
import pandas as pd
data = pd.read_csv("path-of-file.csv")
df = pd.DataFrame(data)
df.to_csv(""path-of-file-2.csv)
print(df)
9. WAP to create a duplicate file for employee.csv containing Empid and Employee Name.
import pandas as pd
data = pd.read_csv("path-of-file.csv", usecols=["empid","Name"])
df = pd.DataFrame(data)
df.to_csv("path-of-file.csv-2", header=["Empid","Employee Name"])
print(df)
13)
import pandas as pd
data = {
"Roll No": [1,2,3,4,5,6],
"StudName":["Teena", "Rinku", "Payel", "Akshay", "Arbin", "Robin"],
"Marks":[90,78,88,89,77,97],
"Class":["11A", "11B", "11C", "11A", "11D", "11E"]
}
df = pd.DataFrame(data)
df.to_csv("student.csv")
14)
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
x = np.arange(1, 5)
plt.plot(x, x*1.5, label='Normal')
plt.plot(x, x*3.0, label='Fast')
plt.plot(x, x/3.0, label='Slow')
plt.legend()
plt.show()
15)
17)
import numpy as np
import matplotlib.pylab as plt
price = [80,70,75,100]
x = np.arange(4)
plt.title("Weekly Change in Onion Prices")
plt.bar(x,price)
plt.xticks(x,["Week 1","Week 2", "Week 3", "Week 4"])
plt.xlabel("Weeks")
plt.ylabel("Prices")
plt.show()
Output:
19)
import matplotlib.pylab as plt
year = [1960, 1970, 1980, 1990, 2000, 2010]
pop_pakistan = [44.91, 58.09, 78.07, 107.7, 138.5, 170.6]
pop_india = [449.48, 553.57, 696.783, 870.133, 1000, 1309.1]
plt.plot(year, pop_india, color='orange', label="India")
plt.plot(year, pop_pakistan, color='g', label="Pakistan")
plt.xlabel('Countries')
plt.ylabel('Population in million')
plt.title('India Pakistan Population till 2010')
plt.legend()
plt.show()
Output:
22)
import matplotlib.pyplot as plt
import numpy as np
prog_lanugages = ('Python', 'C++', 'Java', 'Perl', 'C', 'Lisp')
x = np.arange(len(prog_lanugages))
performance = [10,7,6,4,2,1]
plt.bar(x, performance)
plt.xticks(x, prog_lanugages)
plt.ylabel('Usage')
plt.xlabel("Programming languages")
plt.title('Programming language usage')
plt.show()
Output:
23)
import matplotlib.pyplot as plt
info = ["Gold", "Silver", "Bronze", "Total"]
India = [26,20,20,66]
plt.ylabel("Medal Type")
plt.xlabel("Medal Count")
x = range(len(info))
plt.yticks(x,info)
plt.title("India's Medal Tally in CommonWealth 2021")
plt.barh(x,India,color=["Gold","Silver","Brown","Black"])
plt.show()
Output:
