Python Data Analysis Part 1: Age of Respondents

age.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[["Age"]]

fig = px.scatter(data, y="Age")
fig.show()

data = data.query("(Age >= 10) and (Age <= 75)")
print(f"Rows left: {data.shape[0]:,}")

fig = px.scatter(data, y="Age")
fig.show()

is_integer = lambda row: int(row["Age"]) == row["Age"]
data = data[data.apply(is_integer, axis="columns")]
print(f"Rows left: {data.shape[0]:,}")

data = data.dropna(axis="rows", how="any", subset=["Age"])
print(f"Rows left: {data.shape[0]:,}")

age_counts = data["Age"].value_counts()

fig = px.bar(age_counts, title="Age of respondents")
fig.update_layout(
    xaxis_title = "Age",
    yaxis_title = "Frequency",
    title_x = 0.5,
    showlegend = False
)

fig.show()