app.py

# INSTRUCTIONS:
# 1. Open a "Terminal" by: View --> Terminal OR just the "Terminal" through the hamburger menu
# 2. run in terminal with: streamlit run app.py
# 3. click the "Open in Browser" link that pops up OR click on "Ports" and copy the URL
# 4. Open a Simple Browswer with View --> Command Palette --> Simple Browser: Show
# 5. use the URL from prior steps as intput into this simple browser


import streamlit as st
import altair as alt
from vega_datasets import data
import pandas as pd
 
st.title('Final Project')

st.text("The URL for this app is: https://huggingface.co/spaces/445final/final2.moved")



df = pd.read_csv('State_Employee_Pay.csv')

df_copy = df.copy()
df['Period Pay Rate'] = df['Period Pay Rate'].str.replace(",", "")
df['YTD Gross'] = df['YTD Gross'].str.replace(",", "")
df['Period Pay Rate'] = df['Period Pay Rate'].astype(int)
df['YTD Gross'] = df['YTD Gross'].astype(int)
df = df.dropna()
df = df[df['YTD Gross']!= 0]
# df['Agency'] = df['Agency'].str.lower()
# df['Agency Division'] = df['Agency Division'].str.lower()
# df['Employee Name'] = df['Employee Name'].str.lower()
# df['Position Title'] = df['Position Title'].str.lower()

df_c = df[df['Agency'] == 'corrections']
df_t = df[df['Agency'] == 'transportation']

df1 = df_t

#agency_division_list = df1['Agency Division'].value_counts().tolist()
agency_division_list = df1['Agency Division'].unique().tolist()

selected_division = st.selectbox('Agency Division:',
                                 options=agency_division_list,
                                 index=0)

# horizontal bar chart

def division_positions(selected_division):
    df_db = df1[df1['Agency Division'] == selected_division]
    
    bar_chart_data = df_db.groupby('Position Title').agg(
        employeeCount=('Employee Name', 'count'),
        meanYTDGross=('YTD Gross', 'mean')).reset_index()

    bar_chart_data = bar_chart_data.sort_values('meanYTDGross', ascending=False)

    chart_bar = alt.Chart(bar_chart_data).mark_bar().encode(
        x=alt.X('employeeCount', title = '# of Employees'),
        y=alt.Y('Position Title:O'),
        tooltip=['Position Title', 'employeeCount', alt.Tooltip(
            'meanYTDGross:Q', format='$,.0f', title='Avg YTD Gross')]
               ).properties(title=f'Employee Count by Position in: {selected_division}', 
                 height=alt.Step(20)).interactive()
    return chart_bar


if selected_division:
    final_chart = division_positions(selected_division)
    st.altair_chart(final_chart, use_container_width=True)

st.text('Overall Future Edits: Figure out what to do with positions with 1 employee (if anything), Decide whether to use transportation or corrections data, Re-capitalize agency departments')
st.text('Chart A Future Edits: Order bars by mean YTD Gross, Make all position titles readable, add title')


import altair as alt
import pandas as pd

alt.data_transformers.disable_max_rows()
df_small=df[['Agency','YTD Gross']].copy()

select_bar = alt.selection_point(
    fields=["Agency"],
    on="click",
    clear="true"
)

#summing the barchart but the human services and transit departments are so large you cannot click on the other agencies
# bar_chart = (
#     alt.Chart(df_small)
#     .mark_bar()
#     .encode(
#         y=alt.Y("Agency:N", sort="-x"),
#         x=alt.X("sum(YTD Gross):Q", title="Total Personale Expense"),  # <-- take the mean
#         tooltip=[
#             "Agency:N",
#             alt.Tooltip("mean(YTD Gross):Q", title="Avg YTD Gross", format="$,.0f")
#         ],
#         color=alt.condition(select_bar, alt.value("#4C78A8"), alt.value("#CCCCCC"))
#     )
#     .add_params(select_bar)
#     .properties(width=500, height=800)
# )

# bar_chart = (
#     alt.Chart(df_small)
#     .mark_bar()
#     .encode(
#         y=alt.Y("Agency:N", sort="-x"),
#         x=alt.X("mean(YTD Gross):Q", title="Average Personale Expense"),  # <-- take the mean
#         tooltip=[
#             "Agency:N",
#             alt.Tooltip("mean(YTD Gross):Q", title="Avg YTD Gross", format="$,.0f")
#         ],
#         color=alt.condition(select_bar, alt.value("#4C78A8"), alt.value("#CCCCCC"))
#     )
#     .add_params(select_bar)
#     .properties(width=500, height=800)
# )


bar_chart = (
    alt.Chart(df_small)
    .mark_bar()
    .encode(
        y=alt.Y("Agency:N", sort="-x"),
        x=alt.X("mean(YTD Gross):Q", title="Total Personale Expense"),  # <-- take the mean
        tooltip=[
            "Agency:N",
            alt.Tooltip("mean(YTD Gross):Q", title="Avg YTD Gross", format="$,.0f")
        ],
        color=alt.condition(select_bar, alt.value("#4C78A8"), alt.value("#CCCCCC"))
    )
    .add_params(select_bar)
    .properties(width=500, height=800)
)

# box = (
#     alt.Chart(df_small)
#     .mark_boxplot(size=40)
#     .encode(
#         x=alt.X("Agency:N", title=""),
#         y=alt.Y("YTD Gross:Q", title="Salary Distribution"),
#         opacity=alt.condition(select_bar,alt.value(1),alt.value(0)),
#         color=alt.value("#4C78A8")
#     )  
#     .properties(width=1000, height=800)
# )
# hist = (
#     alt.Chart(df_small)
#     .mark_bar(opacity=0.7)
#     .encode(
#         x=alt.X("YTD Gross:Q", bin=True, title="YTD Gross (binned)"),
#         y=alt.Y("count()", title="Count"),
#         color=alt.value("#4C78A8"),
#         tooltip=[alt.Tooltip("YTD Gross:Q",title="Range"),alt.Tooltip("count():Q",title="Count")]
#     )
#     .transform_filter(select_bar)  
#     .properties(width=400, height=300)
# )


strip = (
    alt.Chart(df)
    .mark_circle(size=60, opacity=0.6)
    .encode(
        x=alt.X("YTD Gross:Q", title="YTD Gross"),
        y=alt.Y("Agency:N", title=""),
        color=alt.value("#4C78A8"),
        tooltip=[
            alt.Tooltip("Position Title:O"),
            alt.Tooltip("YTD Gross:Q", format="$,.0f")
        ]
    )
    .transform_filter(select_bar)   
    .transform_calculate(
        jitter="0.4 * (random() - 0.5)"   
    )
    .encode(
        y=alt.Y("jitter:Q", title="", axis=None) 
    )
    .properties(width=400, height=200)
)
dashboard = bar_chart & strip
dashboard