explore_page.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt

@st.cache_data
def load_data():
    df = pd.read_csv("survey_results_public.csv")
    print(df.shape)
    df = df[["Country", "EdLevel", "YearsCodePro", "Employment", "ConvertedCompYearly"]]
    df = df[df["ConvertedCompYearly"].notnull()]
    df = df[df["Employment"] == "Employed, full-time"]
    df = df.drop("Employment", axis=1)

    country_map = shorten_categories(df.Country.value_counts(), 400)
    df["Country"] = df["Country"].map(country_map)
    df = df[df["ConvertedCompYearly"] <= 250000]
    df = df[df["ConvertedCompYearly"] >= 10000]
    df = df[df["Country"] != "Other"]

    df["YearsCodePro"] = df["YearsCodePro"].apply(clean_experience)
    df["EdLevel"] = df["EdLevel"].apply(clean_education)
    df = df.rename({"ConvertedCompYearly": "Salary"}, axis=1)
    print(df.shape)
    return df


def shorten_categories(categories, cutoff): #this is to remove the extra countries, or the countries which doesnt have many developers
    categorical_map={}
    for i in range(len(categories)):
        if categories.values[i]>=cutoff:
            categorical_map[categories.index[i]]=categories.index[i]
        else:
            categorical_map[categories.index[i]]='Other'
    return categorical_map

def clean_experience(x):
    if x == 'More than 50 years':
        return 50
    if x == 'Less than 1 year':
        return 0.5
    return float(x)


def clean_education(x):
    """
    This function cleans the 'EdLevel' column in a DataFrame.

    Args:
        df (pandas.DataFrame): The DataFrame containing the 'EdLevel' column.

    Returns:
        pandas.DataFrame: The DataFrame with the cleaned 'EdLevel' column.
    """
    x = str(x)  # Convert to string to handle possible NaN values


    if 'Bachelor’s degree' in x:
        return 'Bachelor’s degree'
    elif 'Master’s degree' in x:
        return 'Master’s degree'
    elif 'Professional degree' in x or 'Other doctoral' in x:
        return 'Post grad'
    else:
        return 'Less than a Bachelors'

def show_explore_page():
    st.title("Explore Software Engineer Salaries")

    st.write(
        """
    ### Stack Overflow Developer Survey 2023
    """
    )
    df=load_data()

    data = df["Country"].value_counts()

    fig1, ax1 = plt.subplots()
    ax1.pie(data, labels=data.index, autopct="%1.1f%%", shadow=True, startangle=90, textprops={'fontsize': 5}, labeldistance=1.1)
    ax1.axis("equal")  # Equal aspect ratio ensures that pie is drawn as a circle.

    st.write("""#### Number of Data from different countries""")

    st.pyplot(fig1)
    plt.close(fig1)
    
    st.write(
        """
    #### Mean Salary Based On Country
    """
    )

    data = df.groupby(["Country"])["Salary"].mean().sort_values(ascending=True)
    st.bar_chart(data)

    st.write(
        """
    #### Mean Salary Based On Experience
    """
    )

    data = df.groupby(["YearsCodePro"])["Salary"].mean().sort_values(ascending=True)
    st.line_chart(data)
    
show_explore_page()