Created
January 24, 2021 15:26
-
-
Save Ze1598/88678ed16829f0951450ab563df13d32 to your computer and use it in GitHub Desktop.
Python Data Analysis Part 1: Age of Respondents
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment