Plotting charts for Methods and Frameworks 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("frameworks_extraction_checkpoint.csv")  # Adjust name if needed
10
11# Define column names
12city_col = 'location'
13frameworks_col = 'extracted_methods_frameworks_str'  # <--- Adjust if needed
14
15# Drop rows with missing data
16df = df.dropna(subset=[city_col, frameworks_col]).copy()
17
18# Normalize and split framework strings
19df[city_col] = df[city_col].str.lower().str.strip()
20df[frameworks_col] = df[frameworks_col].str.lower()
21
22# Split framework strings into lists
23df['framework_list'] = df[frameworks_col].str.split(',')
24
25# Explode the list so each framework has its own row
26df_exploded = df.explode('framework_list')
27df_exploded['framework_list'] = df_exploded['framework_list'].str.strip()
28
29# Filter only Sydney entries (data jobs only)
30df_sydney = df_exploded[df_exploded[city_col].str.contains('sydney')]
31
32# Count top frameworks
33top_n = 10
34framework_counts_sydney = df_sydney['framework_list'].value_counts().head(top_n)
35
36# Plot horizontal bar chart in pink shade (without value labels)
37plt.figure(figsize=(12, 8))
38framework_counts_sydney.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
39
40# Formatting
41plt.title(f'Top {top_n} Frameworks in Data Jobs in Sydney', fontsize=16)
42plt.xlabel('Number of Job Listings')
43plt.ylabel('Frameworks / Methods')
44plt.grid(axis='x', linestyle='--', alpha=0.7)
45plt.tight_layout()
46plt.show()

1# Exercise - Top Frameworks Across All Australian Cities (Pink Shade, Horizontal Bar 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("frameworks_extraction_checkpoint.csv")  # Adjust name if needed
12
13# Define column names
14city_col = 'location'
15frameworks_col = 'extracted_methods_frameworks_str'  # <--- Adjust if needed
16
17# Drop rows with missing data
18df = df.dropna(subset=[city_col, frameworks_col]).copy()
19
20# Normalize and split framework strings
21df[city_col] = df[city_col].str.lower().str.strip()
22df[frameworks_col] = df[frameworks_col].str.lower()
23
24# Split framework strings into lists
25df['framework_list'] = df[frameworks_col].str.split(',')
26
27# Explode the list so each framework has its own row
28df_exploded = df.explode('framework_list')
29df_exploded['framework_list'] = df_exploded['framework_list'].str.strip()
30
31# Filter for Australian cities (can add more cities if needed)
32australian_cities_keywords = [
33    'sydney', 'melbourne', 'brisbane', 'perth', 'adelaide', 'canberra',
34    'hobart', 'darwin', 'australia'
35]
36df_aus = df_exploded[df_exploded[city_col].str.contains('|'.join(australian_cities_keywords))]
37
38# Count top frameworks across all Australian cities
39top_n = 10
40framework_counts_aus = df_aus['framework_list'].value_counts().head(top_n)
41
42# Plot horizontal bar chart in pink shade (without value labels)
43plt.figure(figsize=(12, 8))
44framework_counts_aus.sort_values().plot(kind='barh', color='#ff66b2', edgecolor='black')
45
46# Formatting
47plt.title(f'Top {top_n} Frameworks in Data Jobs Across Australian Cities', fontsize=16)
48plt.xlabel('Number of Job Listings')
49plt.ylabel('Frameworks / Methods')
50plt.grid(axis='x', linestyle='--', alpha=0.7)
51plt.tight_layout()
52plt.show()