Plot number of Jobs by Data Recruitment company vs. Direct hiring company for Data Roles in Sydney(Source code)

1# Exercise- Pie Chart: Number of Jobs by Company Type for Data Roles in Sydney
2import pandas as pd
3import matplotlib.pyplot as plt
4from google.colab import files
5
6# Upload CSV file
7uploaded = files.upload()
8
9# Load dataset
10df = pd.read_csv("classified_companies.csv")
11
12# Clean column names and data
13df.columns = df.columns.str.strip().str.lower()
14df['location'] = df['location'].str.lower().str.strip()
15df['sub_classification'] = df['sub_classification'].astype(str).str.lower().str.strip()
16df['company type'] = df['company type'].astype(str).str.strip().str.lower()
17
18# Filter for jobs in Sydney
19sydney_df = df[df['location'].str.contains("sydney")]
20
21# Filter for data-related roles
22keywords = ['data', 'analyst', 'scientist', 'engineer']
23data_roles_df = sydney_df[sydney_df['sub_classification'].str.contains('|'.join(keywords))]
24
25# Count jobs by company type (recruiter vs direct)
26company_type_counts = data_roles_df['company type'].value_counts()
27
28# Relabel for clarity and reorder
29company_type_counts = company_type_counts.rename({
30    'recruiter': 'Recruitment Company',
31    'direct': 'Direct Hiring Company'
32}).reindex(['Direct Hiring Company', 'Recruitment Company'])
33
34# Plot pie chart with pink shades
35colors = ['#ff69b4', '#ffb6c1']  # hot pink, light pink
36plt.figure(figsize=(6, 6))
37company_type_counts.plot(
38    kind='pie',
39    autopct='%1.1f%%',
40    startangle=90,
41    colors=colors,
42    explode=[0.05, 0.05],
43    shadow=True,
44    wedgeprops={'edgecolor': 'black'}
45)
46plt.title("Data Roles in Sydney by Company Type", fontsize=14)
47plt.ylabel("")  # Hide y-label for pie chart
48plt.tight_layout()
49plt.show()