Add data analysis file for scatter plot visualization

data_analysis (1).py

@@ -0,0 +1,57 @@
+# -*- coding: utf-8 -*-
+"""Data analysis.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1rgZ1KKaswBXKXYF_m5svCLsk6eBzLBT9
+"""
+
+!pip install streamlit
+
+import pandas as pd
+import streamlit as st
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+def load_and_scatterplot(year):
+
+    file_path = f"Survey_results_sample_{year}.csv"
+
+    try:
+        data = pd.read_csv(file_path)
+    except FileNotFoundError:
+        st.error(f"File for the year {year} not found!")
+        return None
+
+
+
+    cols = ['Country', 'YearsCodePro', 'ConvertedCompYearly', 'DevType']
+    filtered_data = data[cols].dropna()
+
+    filtered_data['YearsCodePro'] = pd.to_numeric(filtered_data['YearsCodePro'], errors='coerce')
+    filtered_data = filtered_data.dropna(subset=['YearsCodePro'])
+    # Create a scatter plot for YearsCodePro vs ConvertedCompYearly, color-coded by DevType
+    st.write(f"Scatter Plot: Years of Professional Coding Experience vs Yearly Compensation for {year}")
+
+    plt.figure(figsize=(14, 8))
+
+    scatter = sns.scatterplot(
+        data=filtered_data,
+        x='YearsCodePro',
+        y='ConvertedCompYearly',
+        hue='DevType',
+        style='Country',
+        palette='deep',
+        s=100,
+        alpha=0.6
+    )
+
+    scatter.legend(loc='center left', bbox_to_anchor=(1, 0.5), title='Developer Type')
+
+    plt.title(f'YearsCodePro vs ConvertedCompYearly ({year}), colored by DevType', fontsize=16)
+    plt.xlabel('Years of Professional Coding Experience', fontsize=14)
+    plt.ylabel('Yearly Compensation (USD)', fontsize=14)
+
+    st.pyplot(plt)
+