Upload 3 files

Streamlit_app.py

@@ -0,0 +1,194 @@
+# -*- coding: utf-8 -*-
+"""Untitled8.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1SnoorFAucvS1FXD1vzyJnJ-_hoZUfJ_u
+"""
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+
+# Page configuration
+st.set_page_config(
+    page_title="Developer Salary Explorer",
+    page_icon="💻",
+    layout="wide"
+)
+
+@st.cache_data
+def load_data():
+    """Load and preprocess the Stack Overflow survey data"""
+    try:
+        df = pd.read_csv('stackoverflow_survey_single_response.txt')
+
+        # Filter only rows with compensation data
+        df_clean = df[df['converted_comp_yearly'].notna()].copy()
+        df_clean = df_clean[df_clean['converted_comp_yearly'] > 1000]
+
+        # Handle missing values in numeric columns
+        for col in ['years_code', 'years_code_pro', 'age']:
+            df_clean[col] = pd.to_numeric(df_clean[col], errors='coerce')
+            df_clean[col] = df_clean[col].fillna(df_clean[col].median())
+
+        # Create experience levels
+        df_clean['experience_level'] = pd.cut(
+            df_clean['years_code_pro'],
+            bins=[0, 2, 5, 10, 50],
+            labels=['Junior (0-2 yrs)', 'Mid (3-5 yrs)', 'Senior (6-10 yrs)', 'Expert (10+ yrs)']
+        )
+
+        # Simplify country to major regions
+        top_countries = ['United States of America', 'United Kingdom of Great Britain and Northern Ireland',
+                        'Germany', 'India', 'Canada', 'France', 'Australia']
+        df_clean['country'] = df_clean['country'].apply(
+            lambda x: x if x in top_countries else 'Other'
+        )
+
+        # Map education levels to readable names
+        education_map = {
+            1: 'Less than Bachelor',
+            2: 'Bachelor\'s Degree',
+            3: 'Master\'s Degree',
+            4: 'Doctoral Degree',
+            5: 'Professional Degree'
+        }
+        df_clean['education_level'] = df_clean['ed_level'].map(education_map)
+        df_clean['education_level'] = df_clean['education_level'].fillna('Other')
+
+        return df_clean
+
+    except Exception as e:
+        st.error(f"Error loading data: {str(e)}")
+        return pd.DataFrame()
+
+def main():
+    st.title("💻 Developer Salary Explorer")
+    st.markdown("Explore how country, education, and experience influence developer salaries worldwide.")
+
+    # Load data
+    df = load_data()
+
+    if df.empty:
+        st.error("No data loaded. Please check your data file.")
+        return
+
+    st.sidebar.header("🔍 Filter Data")
+
+    # Country filter
+    countries = sorted(df['country'].unique())
+    selected_countries = st.sidebar.multiselect(
+        "Select Countries:",
+        options=countries,
+        default=countries[:3]  # Default to first 3 countries
+    )
+
+    # Education level filter
+    education_levels = sorted(df['education_level'].unique())
+    selected_education = st.sidebar.multiselect(
+        "Select Education Levels:",
+        options=education_levels,
+        default=education_levels
+    )
+
+    # Years of experience slider
+    min_exp, max_exp = st.sidebar.slider(
+        "Years of Professional Experience:",
+        min_value=int(df['years_code_pro'].min()),
+        max_value=int(min(df['years_code_pro'].max(), 40)),  # Cap at 40 for better UX
+        value=(0, 15)
+    )
+
+    # Apply filters
+    filtered_df = df[
+        (df['country'].isin(selected_countries)) &
+        (df['education_level'].isin(selected_education)) &
+        (df['years_code_pro'] >= min_exp) &
+        (df['years_code_pro'] <= max_exp)
+    ]
+
+    # Display metrics
+    st.header("📊 Key Metrics")
+
+    col1, col2, col3, col4 = st.columns(4)
+
+    with col1:
+        median_salary = filtered_df['converted_comp_yearly'].median()
+        st.metric("Median Salary", f"${median_salary:,.0f}")
+
+    with col2:
+        avg_salary = filtered_df['converted_comp_yearly'].mean()
+        st.metric("Average Salary", f"${avg_salary:,.0f}")
+
+    with col3:
+        sample_size = len(filtered_df)
+        st.metric("Sample Size", f"{sample_size:,}")
+
+    with col4:
+        salary_range = f"${filtered_df['converted_comp_yearly'].min():,.0f} - ${filtered_df['converted_comp_yearly'].max():,.0f}"
+        st.metric("Salary Range", salary_range)
+
+    if sample_size == 0:
+        st.warning("No data matches your filters. Please adjust your selection.")
+        return
+
+    # Visualizations
+    st.header("📈 Salary Analysis")
+
+    # 1. Salary by Country
+    st.subheader("🌍 Salary by Country")
+    country_stats = filtered_df.groupby('country')['converted_comp_yearly'].median().sort_values(ascending=False)
+    fig1 = px.bar(
+        x=country_stats.index,
+        y=country_stats.values,
+        title="Median Salary by Country",
+        labels={'x': 'Country', 'y': 'Median Salary (USD)'}
+    )
+    st.plotly_chart(fig1, use_container_width=True)
+
+    # 2. Salary by Education Level
+    st.subheader("🎓 Salary by Education Level")
+    fig2 = px.box(
+        filtered_df,
+        x='education_level',
+        y='converted_comp_yearly',
+        title="Salary Distribution by Education Level"
+    )
+    st.plotly_chart(fig2, use_container_width=True)
+
+    # 3. Salary by Experience
+    st.subheader("📅 Salary vs Experience")
+    fig3 = px.scatter(
+        filtered_df,
+        x='years_code_pro',
+        y='converted_comp_yearly',
+        color='country',
+        title="Salary Growth with Experience",
+        trendline="lowess"
+    )
+    st.plotly_chart(fig3, use_container_width=True)
+
+    # 4. Experience Level Analysis
+    st.subheader("👨‍💻 Salary by Experience Level")
+    exp_stats = filtered_df.groupby('experience_level')['converted_comp_yearly'].median()
+    fig4 = px.bar(
+        x=exp_stats.index,
+        y=exp_stats.values,
+        title="Median Salary by Experience Level"
+    )
+    st.plotly_chart(fig4, use_container_width=True)
+
+    # Data Table
+    st.header("📋 Detailed Data View")
+    if st.checkbox("Show filtered data table"):
+        display_cols = ['country', 'education_level', 'experience_level', 'years_code_pro', 'converted_comp_yearly']
+        st.dataframe(
+            filtered_df[display_cols].sort_values('converted_comp_yearly', ascending=False),
+            use_container_width=True
+        )
+
+if __name__ == "__main__":
+    main()