Plot charts for visualizing number of Data Jobs(Source code)

1#Data Jobs in sydney
2import pandas as pd
3import matplotlib.pyplot as plt
4from google.colab import files
5uploaded = files.upload()
6df = pd.read_csv('classified_companies.csv')
7
8
9# Filter for Sydney only (case-insensitive match)
10df_sydney = df[df['location'].str.contains('sydney', case=False, na=False)]
11
12# Filter for data jobs using sub_classification column
13# You can adjust the keywords as needed
14data_keywords = ['data', 'analytics', 'machine learning', 'ai', 'artificial intelligence', 'ml', 'big data']
15df_data_jobs = df_sydney[df_sydney['sub_classification'].str.contains('|'.join(data_keywords), case=False, na=False)]
16
17# Count of each sub-classification among data jobs
18data_job_counts = df_data_jobs['sub_classification'].value_counts()
19
20# Plotting
21plt.figure(figsize=(10, 6))
22data_job_counts.plot(kind='bar', color='#ff69b4')  # pinkish color
23plt.title('Data Jobs in Sydney', fontsize=14)
24plt.xlabel('Sub-classification')
25plt.ylabel('Number of Jobs')
26plt.xticks(rotation=45, ha='right')
27plt.tight_layout()
28plt.grid(axis='y', linestyle='--', alpha=0.7)
29plt.show()

1import pandas as pd
2import matplotlib.pyplot as plt
3
4from google.colab import files
5uploaded = files.upload()
6df = pd.read_csv('classified_companies.csv')
7
8# Step 2: Filter valid locations in Australia
9df = df[df['location'].notna()]
10
11# Step 3: Identify data-related jobs
12data_keywords = ['data', 'analytics', 'machine learning', 'ai', 'artificial intelligence', 'ml', 'big data']
13df_data = df[df['sub_classification'].str.contains('|'.join(data_keywords), case=False, na=False)]
14
15# Step 4: Extract city from location
16df_data['city'] = df_data['location'].str.extract(r'(^[A-Za-z ]+)')
17
18# Step 5: Group by city and sub-classification
19grouped = df_data.groupby(['city', 'sub_classification']).size().unstack(fill_value=0)
20
21# Optional: Limit to top N cities
22top_cities = df_data['city'].value_counts().head(10).index
23grouped = grouped.loc[grouped.index.isin(top_cities)]
24
25# Step 6: Plot using pink/violet-only shades
26plt.figure(figsize=(18, 10))
27color_palette = [
28    '#7B3294',  # deep violet
29    '#C51B7D',  # dark pink
30    '#DE77AE',  # medium pink
31    '#F1B6DA',  # pastel pink
32    '#E781BF',  # rosy pink
33    '#B03060',  # raspberry
34    '#D36BA4',  # orchid
35    '#CC6699',  # dusty rose
36    '#FF66CC',  # bright pink
37    '#993366'   # wine pink
38]
39
40grouped.plot(kind='bar', stacked=True, color=color_palette, edgecolor='black', figsize=(18, 10))
41
42plt.title('Data Job Distribution Across Australian Cities', fontsize=20)
43plt.xlabel('City', fontsize=14)
44plt.ylabel('Number of Jobs', fontsize=14)
45plt.xticks(rotation=45, ha='right', fontsize=12)
46plt.yticks(fontsize=12)
47plt.legend(title='Sub-classification', bbox_to_anchor=(1.02, 1), loc='upper left', fontsize=10)
48plt.tight_layout()
49plt.grid(axis='y', linestyle='--', alpha=0.6)
50plt.show()