Spaces:
Sleeping
Sleeping
File size: 2,397 Bytes
c85b155 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 |
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
def shorten_categories(categories, cutoff):
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):
if 'Bachelor’s degree' in x:
return 'Bachelor’s degree'
if 'Master’s degree' in x:
return 'Master’s degree'
if 'Professional degree' in x or 'Other doctoral' in x:
return 'Post grad'
return 'Less than a Bachelors'
@st.cache_data
def load_data():
df = pd.read_csv("survey_results_public.csv")
df = df[["Country", "EdLevel", "YearsCodePro", "Employment", "ConvertedCompYearly"]]
df = df.rename({"ConvertedCompYearly": "Salary"}, axis=1)
df = df[df["Salary"].notnull()]
df = df.dropna()
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["Salary"] <= 250000]
df = df[df["Salary"] >= 10000]
df = df[df['Country'] != 'Other']
df['YearsCodePro'] = df['YearsCodePro'].apply(clean_experience)
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 Developer Survey 2022""")
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") # Equal aspect ratio ensures that pie is drawn as a circle.
st.write("""#### Number of Data from different countries""")
st.pyplot(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) |