Years of Experience (Source code)

1import pandas as pd
2import numpy as np
3import matplotlib.pyplot as plt
4import seaborn as sns
5import re
6from google.colab import files
7
8uploaded = files.upload()
9df = pd.read_csv("seek_jobs.csv")
10
11text_cols = [col for col in df.columns if 'description' in col.lower() or 'details' in col.lower()]
12df['combined_text'] = df[text_cols].fillna('').agg(' '.join, axis=1)
13
14
15def extract_experience(text):
16    text = text.lower()
17
18    patterns = [
19        r'(\d+)[\s\-to]+(\d+)\s+years?\s+(?:of\s+)?experience',  
20        r'(\d+)\+?\s+years?\s+(?:of\s+)?experience',             
21        r'more than (\d+)\s+years?\s+(?:of\s+)?experience',      
22        r'minimum of (\d+)\s+years?\s+(?:of\s+)?experience',     
23        r'at least (\d+)\s+years?\s+(?:of\s+)?experience',       
24        r'requires? (\d+)\s+years?\s+(?:of\s+)?experience',      
25    ]
26
27    min_exp, max_exp = [], []
28    for pattern in patterns:
29        matches = re.findall(pattern, text)
30        for match in matches:
31            if isinstance(match, tuple):
32                val1, val2 = int(match[0]), int(match[1])
33            else:
34                val1 = val2 = int(match)
35
36            
37            if 0 < val1 <= 40 and 0 < val2 <= 40:
38                min_exp.append(val1)
39                max_exp.append(val2)
40
41    if min_exp and max_exp:
42        min_val, max_val = min(min_exp), max(max_exp)
43    elif min_exp:
44        min_val = max_val = min(min_exp)
45    else:
46        return pd.Series([np.nan, np.nan])
47
48    return pd.Series([min_val, max_val])
49
50
51df[['min_experience', 'max_experience']] = df['combined_text'].apply(extract_experience)
52
53
54
55df_exp = df.dropna(subset=['min_experience', 'max_experience'])
56
57
58# Min/Max experience by city
59'''plt.figure(figsize=(28, 10))
60cities = avg_exp.index
61plt.plot(cities, avg_exp['min_experience'], marker='o', label='Min Experience', color='#ffb6c1', linewidth=2)
62plt.plot(cities, avg_exp['max_experience'], marker='o', label='Max Experience', color='#db7093', linewidth=2)
63
64# Optional: fill between min and max for better visual
65plt.fill_between(cities, avg_exp['min_experience'], avg_exp['max_experience'], color='#f8bbd0', alpha=0.3)
66
67plt.title('Line Chart of Min and Max Years of Experience by City', fontsize=14, weight='bold')
68plt.ylabel('Years of Experience', fontsize=12)
69plt.xlabel('City', fontsize=12)
70plt.xticks(rotation=45, ha='right', fontsize=10)
71plt.yticks(fontsize=10)
72plt.grid(True, linestyle='--', alpha=0.6)
73plt.legend()
74plt.tight_layout()
75plt.show()'''
76
77
78
79def bucket_exp(x):
80    if x <= 3: return '0-3'
81    elif x <= 5: return '3+'
82    elif x <= 7: return '5-7'
83    elif x <= 10: return '5+'
84    else: return '10+'
85
86df_exp['exp_bucket'] = df_exp['min_experience'].apply(bucket_exp)
87bucket_counts = pd.crosstab(df_exp['location'], df_exp['exp_bucket'])
88
89
90
91# Stacked experience range count per city with pinkish theme
92'''bucket_counts.plot(
93    kind='bar',
94    stacked=True,
95    figsize=(28, 10),  # Adjusted figsize
96    color=['#ffb6c1', '#ff69b4', '#db7093', '#c71585'],  # Pink shades
97    edgecolor='black'
98)
99plt.title('Stacked Chart of Experience Buckets by City', fontsize=14, weight='bold')
100plt.ylabel('Job Count', fontsize=12)
101plt.xlabel('City', fontsize=12)
102plt.xticks(rotation=45, ha='right', fontsize=10, rotation_mode='anchor')  # Adjust rotation and alignment
103plt.yticks(fontsize=10)
104plt.legend(title='Experience Bucket')
105plt.grid(axis='y', linestyle='--', alpha=0.6)
106plt.tight_layout()
107plt.show()'''
108
109
110
111print(df_exp[['job_title', 'min_experience', 'max_experience']])
112
113
114
115salary_cols = [col for col in df.columns if 'salary' in col.lower()]
116print("Salary columns found:", salary_cols)
117
118
119salary_col = salary_cols[0] if salary_cols else None
120
121# Filter for 'Data Analyst' in Sydney
122'''if salary_col:
123    df_filtered = df_exp[
124        df_exp['job_title'].str.lower().str.contains('data analyst', na=False) &
125        df_exp['location'].str.lower().str.contains('sydney', na=False) &
126        df_exp[salary_col].notnull()
127    ]
128
129    # Scatter plot: Salary vs Experience
130    plt.figure(figsize=(10, 6))
131    plt.scatter(df_filtered['min_experience'], df_filtered[salary_col], alpha=0.7, color='#db7093', edgecolor='black')
132    plt.title('Salary vs. Years of Experience for Data Analysts in Sydney', fontsize=14, weight='bold')
133    plt.xlabel('Years of Experience (Min)', fontsize=12)
134    plt.ylabel('Salary', fontsize=12)
135    plt.grid(True, linestyle='--', alpha=0.6)
136    plt.tight_layout()
137    plt.show()
138else:
139    print("No salary column found to plot.")'''