Plotting charts for tool extracted from dataset(Source code)

1import pandas as pd
2import matplotlib.pyplot as plt
3from google.colab import files
4
5# Upload the CSV file
6uploaded = files.upload()
7
8# Load dataset
9df = pd.read_csv("extraction_checkpoint.csv")
10
11# Column names (adjust if needed)
12city_col = 'location'
13tools_col = 'extracted_tools_str'
14
15# Drop missing values
16df = df.dropna(subset=[city_col, tools_col]).copy()
17
18# Lowercase and split tool strings
19df[tools_col] = df[tools_col].str.lower()
20df['tool_list'] = df[tools_col].str.split(',')
21
22# Explode tool list to individual rows
23df_exploded = df.explode('tool_list')
24df_exploded['tool_list'] = df_exploded['tool_list'].str.strip()
25
26# Filter for Sydney
27df_sydney = df_exploded[df_exploded[city_col].str.lower().str.contains('sydney')]
28
29# Remove known programming languages
30languages_to_exclude = {
31    'python', 'r', 'go', 'java', 'c', 'c++', 'c#', 'scala', 'typescript',
32    'javascript', 'sql', 'ruby', 'rust', 'kotlin', 'perl', 'php', 'swift',
33    'matlab', 'dart', 'bash', 'powershell', 'haskell', 'react', 'agile', 'node.js'
34}
35df_sydney = df_sydney[~df_sydney['tool_list'].isin(languages_to_exclude)]
36
37# Count tool frequency
38top_n = 10
39tool_counts = df_sydney['tool_list'].value_counts().head(top_n)
40
41# Plot horizontal bar chart
42plt.figure(figsize=(12, 8))
43tool_counts.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
44
45plt.title(f'Top {top_n} Tools Used in Sydney Data Jobs ', fontsize=16)
46plt.xlabel('Number of Jobs')
47plt.ylabel('Tool')
48plt.grid(axis='x', linestyle='--', alpha=0.7)
49plt.tight_layout()
50plt.show()

1#Tools across in Australia
2import pandas as pd
3import matplotlib.pyplot as plt
4from google.colab import files
5
6# Upload the CSV file
7uploaded = files.upload()
8
9# Load dataset
10df = pd.read_csv("extraction_checkpoint.csv")
11
12# Column names (adjust if needed)
13city_col = 'location'
14tools_col = 'extracted_tools_str'
15
16# Drop missing values
17df = df.dropna(subset=[city_col, tools_col]).copy()
18
19# Lowercase and split tool strings
20df[tools_col] = df[tools_col].str.lower()
21df['tool_list'] = df[tools_col].str.split(',')
22
23# Explode tool list to individual rows
24df_exploded = df.explode('tool_list')
25df_exploded['tool_list'] = df_exploded['tool_list'].str.strip()
26
27# Filter for Australian cities (basic keyword match, can be refined)
28df_au = df_exploded[df_exploded[city_col].str.lower().str.contains(
29    'sydney|melbourne|brisbane|perth|adelaide|canberra|hobart|darwin'
30)]
31
32# Remove known programming languages
33languages_to_exclude = {
34    'python', 'r', 'go', 'java', 'c', 'c++', 'c#', 'scala', 'typescript',
35    'javascript', 'sql', 'ruby', 'rust', 'kotlin', 'perl', 'php', 'swift',
36    'matlab', 'dart', 'bash', 'powershell', 'haskell', 'react', 'agile', 'node.js'
37}
38df_au = df_au[~df_au['tool_list'].isin(languages_to_exclude)]
39
40# Count tool frequency
41top_n = 10
42tool_counts = df_au['tool_list'].value_counts().head(top_n)
43
44# Plot horizontal bar chart
45plt.figure(figsize=(12, 8))
46tool_counts.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
47
48plt.title(f'Top {top_n} Tools Used in Data Jobs Across Australian Cities', fontsize=16)
49plt.xlabel('Number of Jobs')
50plt.ylabel('Tool')
51plt.grid(axis='x', linestyle='--', alpha=0.7)
52plt.tight_layout()
53plt.show()