Plotting charts for Programming Languages 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("language_extraction_checkpoint.csv")
10
11# Define column names
12city_col = 'location'
13lang_col = 'extracted_programming_languages_str'  # Adjust if needed
14
15# Drop rows with missing data
16df = df.dropna(subset=[city_col, lang_col]).copy()
17
18# Normalize and split language strings
19df[lang_col] = df[lang_col].str.lower()
20df['language_list'] = df[lang_col].str.split(',')
21
22# Explode list to rows
23df_exploded = df.explode('language_list')
24df_exploded['language_list'] = df_exploded['language_list'].str.strip()
25
26# Filter for Sydney rows
27df_sydney = df_exploded[df_exploded[city_col].str.lower().str.contains('sydney')]
28
29# Count frequency of each language
30top_n = 10
31language_counts = df_sydney['language_list'].value_counts().head(top_n)
32
33# Plot horizontal bar chart with pink shading
34plt.figure(figsize=(12, 8))
35language_counts.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
36
37plt.title(f'Top {top_n} Programming Languages Used in Sydney Data Jobs', fontsize=16)
38plt.xlabel('Number of Jobs')
39plt.ylabel('Programming Language')
40plt.grid(axis='x', linestyle='--', alpha=0.7)
41plt.tight_layout()
42plt.show()

1# Top Programming Languages Across All Australian Cities
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("language_extraction_checkpoint.csv")
12
13# Define column names (adjust if needed)
14city_col = 'location'
15lang_col = 'extracted_programming_languages_str'
16
17# Drop rows with missing data
18df = df.dropna(subset=[city_col, lang_col]).copy()
19
20# Normalize text and split language strings
21df[lang_col] = df[lang_col].str.lower()
22df['language_list'] = df[lang_col].str.split(',')
23
24# Explode the list to individual rows
25df_exploded = df.explode('language_list')
26df_exploded['language_list'] = df_exploded['language_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 frequency of each language
36top_n = 10
37language_counts_aus = df_aus['language_list'].value_counts().head(top_n)
38
39# Plot horizontal bar chart with pink shade and no labels
40plt.figure(figsize=(12, 8))
41language_counts_aus.sort_values().plot(
42    kind='barh',
43    color='#ff66b2',
44    edgecolor='black'
45)
46
47# Title and axis labels
48plt.title(f'Top {top_n} Programming Languages in Data Jobs Across Australian Cities', fontsize=16)
49plt.xlabel('Number of Job Listings')
50plt.ylabel('Programming Language')
51plt.grid(axis='x', linestyle='--', alpha=0.7)
52plt.tight_layout()
53plt.show()