Plotting charts for Soft skills extracted from dataset(Source code)

1import pandas as pd
2import matplotlib.pyplot as plt
3from google.colab import files
4
5# ---- Upload CSV file ---- #
6uploaded = files.upload()
7
8# ---- Load dataset ---- #
9df = pd.read_csv("skills_extraction_checkpoint.csv")
10
11# Define column names
12city_col = 'location'
13soft_skill_col = 'extracted_soft_skills_str'  # Change if needed
14
15# Drop rows with missing data
16df = df.dropna(subset=[city_col, soft_skill_col]).copy()
17
18# Normalize and split soft skill strings
19df[soft_skill_col] = df[soft_skill_col].str.lower()
20df['soft_skill_list'] = df[soft_skill_col].str.split(',')
21
22# Explode to individual soft skills
23df_exploded = df.explode('soft_skill_list')
24df_exploded['soft_skill_list'] = df_exploded['soft_skill_list'].str.strip()
25
26# Filter only Sydney entries
27df_sydney = df_exploded[df_exploded[city_col].str.lower().str.contains('sydney')]
28
29# Count top soft skills
30top_n = 10
31soft_skill_counts = df_sydney['soft_skill_list'].value_counts().head(top_n)
32
33# Plot horizontal bar chart in pink shade (without value labels)
34plt.figure(figsize=(12, 8))
35soft_skill_counts.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
36
37# Formatting
38plt.title(f'Top {top_n} Soft Skills in Sydney Data Jobs', fontsize=16)
39plt.xlabel('Number of Job Listings')
40plt.ylabel('Soft Skill')
41plt.grid(axis='x', linestyle='--', alpha=0.7)
42plt.tight_layout()
43plt.show()

1# Exercise 10 - Top Soft Skills for Data Jobs Across Australian Cities (No Value Labels, Pink Chart)
2
3import pandas as pd
4import matplotlib.pyplot as plt
5from google.colab import files
6
7# ---- Upload CSV file ---- #
8uploaded = files.upload()
9
10# ---- Load dataset ---- #
11df = pd.read_csv("skills_extraction_checkpoint.csv")
12
13# Define column names
14city_col = 'location'
15soft_skill_col = 'extracted_soft_skills_str'  # Change if needed
16
17# Drop rows with missing data
18df = df.dropna(subset=[city_col, soft_skill_col]).copy()
19
20# Normalize and split soft skill strings
21df[soft_skill_col] = df[soft_skill_col].str.lower()
22df['soft_skill_list'] = df[soft_skill_col].str.split(',')
23
24# Explode to individual soft skills
25df_exploded = df.explode('soft_skill_list')
26df_exploded['soft_skill_list'] = df_exploded['soft_skill_list'].str.strip()
27
28# Filter for rows where the location is in Australia
29australian_cities_keywords = [
30    'sydney', 'melbourne', 'brisbane', 'perth', 'adelaide', 'canberra',
31    'hobart', 'darwin', 'australia'
32]
33df_aus = df_exploded[df_exploded[city_col].str.lower().str.contains('|'.join(australian_cities_keywords))]
34
35# Count top soft skills
36top_n = 10
37soft_skill_counts_aus = df_aus['soft_skill_list'].value_counts().head(top_n)
38
39# Plot horizontal bar chart in pink shade (without value labels)
40plt.figure(figsize=(12, 8))
41soft_skill_counts_aus.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
42
43# Formatting
44plt.title(f'Top {top_n} Soft Skills in Data Jobs Across Australian Cities', fontsize=16)
45plt.xlabel('Number of Job Listings')
46plt.ylabel('Soft Skill')
47plt.grid(axis='x', linestyle='--', alpha=0.7)
48plt.tight_layout()
49plt.show()

1#General chart for soft skills across all jobs in sydney
2
3import pandas as pd
4import matplotlib.pyplot as plt
5from google.colab import files
6
7# ---- Upload CSV file ---- #
8uploaded = files.upload()
9
10# ---- Load dataset ---- #
11df = pd.read_csv("skills_extraction_checkpoint.csv")
12
13# Define column names
14city_col = 'location'
15soft_skill_col = 'extracted_soft_skills_str'  # Change if needed
16
17# Drop rows with missing data
18df = df.dropna(subset=[city_col, soft_skill_col]).copy()
19
20# Normalize and split soft skill strings
21df[soft_skill_col] = df[soft_skill_col].str.lower()
22df['soft_skill_list'] = df[soft_skill_col].str.split(',')
23
24# Explode to individual soft skills
25df_exploded = df.explode('soft_skill_list')
26df_exploded['soft_skill_list'] = df_exploded['soft_skill_list'].str.strip()
27
28# Filter only Sydney entries (all jobs, not data jobs)
29df_sydney_all_jobs = df_exploded[df_exploded[city_col].str.lower().str.contains('sydney')]
30
31# Count top soft skills
32top_n = 10
33soft_skill_counts_sydney = df_sydney_all_jobs['soft_skill_list'].value_counts().head(top_n)
34
35# Plot horizontal bar chart in pink shade (without value labels)
36plt.figure(figsize=(12, 8))
37soft_skill_counts_sydney.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
38
39# Formatting
40plt.title(f'Top {top_n} Soft Skills in All Jobs in Sydney', fontsize=16)
41plt.xlabel('Number of Job Listings')
42plt.ylabel('Soft Skill')
43plt.grid(axis='x', linestyle='--', alpha=0.7)
44plt.tight_layout()
45plt.show()