Python Data Analysis Part 2: Annual Compensation

compensation.py

import pandas as pd
from os import getcwd, path
import plotly.express as px
import plotly.offline as pyo
pyo.init_notebook_mode()

path_to_data = path.join(getcwd(), "data", "survey_results_public.csv")
data = pd.read_csv(path_to_data)

data = data[["ConvertedComp"]]

data = data[(data["ConvertedComp"] >= 0) & (data["ConvertedComp"] <= 200_000)]
print(f"Rows left: {data.shape[0]:,}")

bin_labels = [
    f"[{int(i / 1_000):,}K, {int((i + 15_000) / 1_000):,}K)" 
    for i in range(0, 200_001, 15_000)
]

compensation_bins = pd.IntervalIndex.from_tuples(
    [
        (i, i + 15_000) 
        for i in range(0, 200_001, 15_000)
    ],
    closed="left"
)

data = pd.cut(
    data["ConvertedComp"], 
    compensation_bins, 
    precision=0,
    include_lowest=True
)

data.sort_values(inplace=True)

data = data.astype("str")

fig = px.histogram(
    data,
    title="Annual Compensation (USD)",
)

fig.update_layout(
    xaxis = {
        "tickmode": "array",
        "tickvals": data.unique(),
        "ticktext": bin_labels
    },
    xaxis_title = "Annual Compensation",
    yaxis_title = "Frequency",
    title_x = 0.5,
    bargap = 0,
    showlegend = False
)
fig.update_traces(
    marker = {
        "line": {
            "width": 2, 
            "color": "DarkSlateGrey"
        }
    }
)
fig.show()