explore_page.py

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

def shorten_categories(categories, cutoff):
    categorical_map = {}
    # cutoff number we can play around with
    for i in range(len(categories)):
      # for country count_value equal or greater than the cutoff, keep
        if categories.values[i] >= cutoff:
            categorical_map[categories.index[i]] = categories.index[i]
        else:
          # otherwise group them as 'Other'
            categorical_map[categories.index[i]] = 'Other'
    return categorical_map 


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


@st.cache
def clean_education(x):
  # keep Bachelor's degree
    if 'Bachelor’s degree' in x:
        return 'Bachelor’s degree'
        # keep master's degree
    if 'Master’s degree' in x:
        return 'Master’s degree'
        # group doctorates and assign to Post grad
    if 'Professional degree' in x or 'Other doctoral' in x:
        return 'Post grad'
    return 'Less than a Bachelors'

def  load_data():
     df= pd.read_csv('survey_results_public.csv')
     df = df[['Employment', 'Country', 'EdLevel', 'YearsCodePro', 'ConvertedCompYearly']]
     df = df.rename({'ConvertedCompYearly': 'Salary'}, axis=1)
     df= df[df["Salary"].notnull()]
     df= df.dropna()
     df = df.drop('Employment', axis=1)
     country_map = shorten_categories(df.Country.value_counts(), 500)
     df['Country']= df['Country'].map(country_map)
     df = df[df['Salary'] <= 250000]
     df = df[df['Salary'] >= 100000]
     df = df[df['Country'] != 'Other']
     df['YearsCodePro'] = df['YearsCodePro'].apply(cleanexperience)
     df['EdLevel'] = df['EdLevel'].apply(clean_education)
     return df
 

df = load_data()

def show_explore_page():
    st.title("Explore Software Engineer Salaries")
    
    st.write(
        '''
        ### Stack Overflow Survey 2020
        '''
        )
    
    data= df["Country"].value_counts()
    
    
    fig1, ax1 = plt.subplots()
    ax1.pie(data, labels=data.index, autopct= '%1.1f%', shadow=True, startangle=90)
    ax1.axis("equal")
    
    
    st.write('''#### Number of Data from different  countries''')
    
    st.pyplot(fig1)