# Solutions for Data Analysis and Visualization (UPC: 2343012002)

S.No. 1673

# SECTION A

# Q1 (a)

import matplotlib.pyplot as plt

rainfall = [5, 2, 7, 8, 2]

days = [1, 3, 5, 1, 9]

plt.plot(days, rainfall, 'ro', markersize=10)

plt.title("Rainfall over Days")

plt.xlabel("Days")

plt.ylabel("Rainfall")

plt.show()

# Q1 (b)

import pandas as pd

company = pd.DataFrame({'Name': ['Sangeeta', 'Sarika', 'Sangeeta', 'Babita', 'Sarika'], 'Age': [18, 30,
45, 32, 25]})

# (i)

company['Name'].unique()

# (ii)

company.groupby('Name')['Age'].mean()

Q1 (c)

section1 = pd.DataFrame({'RollNo': [1,2,3, 4], 'Name': ['Abhav', 'Vihaan','Chitra','Devansh']})

section2 = pd.DataFrame({'RollNo': [1,5,3, 2], 'Name': ['Roni', 'Kabeer','Ishani','Vihaan']})

# (i)

print(section1)

# (ii)

merged = pd.merge(section2, section1, on='Name', how='inner')

print(merged)

# (iii)
common = pd.merge(section1, section2, on=['Name', 'RollNo'])

print(common)

# Q1 (d)

al = np.zeros((2, 3))

[[0,0,0],[0,0,0]]

a2 = [[3, 4, 5], [7, 8, 9]]

print(np.add(al, a2))

[[3.,4.,5.,],[7.,8.,9.]]

a1=np.append(a1,a2,axis=0)

print(a1)

[[0,0,0],[0,0,0], [3.,4.,5.,],[7.,8.,9.]]

print('shape of array',a1.shape)

(4,3)

# Q1 (e)

empSalary = np.array([4000, 5200, 6100, 7000, 4900, 8000, 3000, 9200, 6300, 4800])

# (i)

len(empSalary[empSalary>5000])# (ii)

incentive = empSalary * 0.1

print("Incentives:", incentive)

# Q1 (f)

data = pd.DataFrame([[2, 4, 6], [np.NaN, 8, 10], [np.NaN, 12, np.NaN], [np.NaN, np.NaN, np.NaN]])

print(data)

0 1 2

0 2.0 4.0 6.0

1 NaN 8.0 10.0

2 NaN 12.0 NaN

3 NaN NaN NaN

print(data.dropna(thresh=2))
 0 1 2

0 2.0 4.0 6.0

1 NaN 8.0 10.0

print(data.fillna(method="ffill", limit=2))

0 1 2

0 2.0 4.0 6.0

1 2.0 8.0 10.0

2 2.0 12.0 10.0

3 NaN 12.0 10.0

# SECTION B

# Q2 (a)

df = pd.DataFrame(np.arange(12).reshape(4, 3), index=[['North', 'North', 'South', 'South'], [1, 2, 1,

df.index.names = ['key1', 'key2']

print(df)

df1 = df.swaplevel('key1', 'key2')

print(df1)

df2 = df1.sort_index(level=0)

print(df2)

# Q2 (b)

markSheet = np.random.randint(60, 101, size=(2, 3))

print(markSheet)

print("Datatype:", markSheet.dtype)

print("Shape:", markSheet.shape)

print("Dimension:", markSheet.ndim)

# Q2 (c)
itemRate = pd.DataFrame({'Item': ['Apples', 'Oranges'], 'Rate': [220, 90]})

itemRate['Rate'] *= 2

print(itemRate)

print("Item with Min Rate:", itemRate.loc[itemRate['Rate'].idxmin()])

Q 3 import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

# DataFrame

data = {

'Name': ['Mohan', 'Sohan', 'Jeevan', 'Gita', 'Meenu', 'Gopal', 'Rajeev'],

'Hours_studied': [2.5, 4.0, 6.0, 8.0, 10.0, 1.0, 5.0],

'Marks_obtained': [40, 52, 64, 70, 90, 10, 60]

df_Student = pd.DataFrame(data)

# 1. Students with maximum marks

max_marks = df_Student['Marks_obtained'].max()

top_students = df_Student[df_Student['Marks_obtained'] == max_marks]['Name'].tolist()

print("Students with maximum marks:", top_students)

# 2. Average hours studied

avg_hours = df_Student['Hours_studied'].mean()

print("Average hours studied:", avg_hours)

# 3. Correlation and Covariance

correlation = df_Student[['Hours_studied', 'Marks_obtained']].corr()

covariance = df_Student[['Hours_studied', 'Marks_obtained']].cov()

print("Correlation:\n", correlation)

print("Covariance:\n", covariance)
# 4. Heatmap

sns.heatmap(df_Student[['Hours_studied', 'Marks_obtained']].corr(), annot=True, cmap='coolwarm')

plt.title('Heatmap: Hours Studied vs Marks Obtained')

plt.show()

i.

[0 1 2 3 4 5]

ii.

[[1 2 3]

[4 6 8]]

iii.

[[2. 1. 0.66666667]

[0.5 0.33333333 0.25 ]]

iv.

1 [4 6 8] [[1 2 3]]

v.

[0]

Q 4 a)

Q4 (b)

df=pd.DataFrame({'person':['A','B','C','D','E','A','B','C','D'],'sales':
[1000,300,400,500,800,1000,500,700,50],'quarter':[1,1,1,1,1,2,2,2,2],'country':
['US','Japna','Brazil','UK','US','Brazil','Japan','Brazil','US']})sns.boxplot(x='sales', data=data)

max_sales=df[df['country']=='Brazil']['sales'].max()

min_sales=df[df['country']=='Brazil']['sales'].min()

df.groupby('country')['sales'].sum()

max_avg_sales=df.groupby('person')['sales'].mean().max()

df[df['sales']==max_avg_sales]['person']
df['sales'].describe()

boxplot = df.boxplot(column='sales')

plt.show()

# Q5 (a)

c1 = np.arange(0, 24)

c2 = c1.reshape((2, 12))

c2[:, 3:] = 0

print(c1)

print(c2)

print(c1 * 2)

print(c2.reshape((3, 8)))

# Q5 (b)

excel_data = pd.DataFrame({

'Employee id': [101, 102, 103, 104, 105, 106],

'Department': ['CS', 'CS', 'CS', 'English', 'English', 'English'],

'Salary': [2000, 2002, 2040, 2045, 2030, 2006],

'Age': [24, 23, 34, 39, 43, 34]

})

excel_data.to_excel("data.xlsx", index=False)

df1 = pd.read_excel("data.xlsx", index_col='Employee id')

fig, axes = plt.subplots(1, 2)

df1.plot.scatter(x='Salary', y='Age', ax=axes[0], title='Salary vs Age')

df1['Salary_bins'] = pd.cut(df1['Salary'], 3)

df1['Salary_bins'].value_counts().plot(kind='bar', ax=axes[1])

plt.savefig("Employees.png")

# Q6 (a)

s1 = pd.Series([5, 0, -4, 8])

print(s1)

print(s1.rank())
data1 = pd.DataFrame({'One': ['a', 'b'] * 2 + ['b'], 'Two': [21, 22, 21, 23, 24]})

print(data1)

data2 = data1.drop_duplicates(['One', 'Two'], keep='last')

print(data2)

df1 = pd.DataFrame({'A': [21, 32], 'B': [27, 30]})

df2 = pd.DataFrame({'A': [23, 41]})

df2['A'][1] = df2['A'][1] + 10

print(df1)

print(df2)

print(df2 > df1['B'].min())

# Q6 (b)

ages = np.array([20, 22, 25, 27, 21, 23, 37, 31, 61, 45, 41, 32])

categories = pd.cut(ages, bins=[18, 25, 35, 60, 100], labels=['Youth', 'YoungAdult', 'MiddleAged',
'Senior'])

print(categories.value_counts())

quantile_bins = pd.qcut(ages, q=4)

print(quantile_bins.value_counts())

# Q7

empData = pd.DataFrame({

'Gender': ['Male', 'Male', 'Male', 'Male', 'Female', 'Female', 'Female', 'Female', 'Female', 'Male',
'Male', 'Male'],

'Role': ['Data Analyst']*3 + ['Data Scientist']*3 + ['Manager']*3 + ['Data Analyst', 'Data Scientist',
'Manager'],

'Experience': [1, 1, 3, 5, 6, 1, 2, 3, 5, 6, 10, 11],

'Salary': [48000, 42000, 51000, 62000, 71000, 73000, 82000, 87000, 91000, 45000, 56000, 66000]

})

# (a)

print(empData)

# (b)

print(empData.groupby('Role')['Salary'].sum())
# (c)

print(empData[empData['Gender'] == 'Female'].groupby('Role').size())

# (d)

print(empData.groupby('Gender')['Salary'].agg(['max', 'min']))

# (e)

avg_salary = empData['Salary'].mean()

empData = empData[empData['Salary'] >= avg_salary]

print(empData)