Skip to content

Instantly share code, notes, and snippets.

@gustheman
Last active October 15, 2022 22:21
Show Gist options
  • Save gustheman/c26cc3966820190f64c1d45168d4d0e6 to your computer and use it in GitHub Desktop.
Save gustheman/c26cc3966820190f64c1d45168d4d0e6 to your computer and use it in GitHub Desktop.
This is a simple function to plot results from the Kaggle Kernel Survey (2021 and 2022). It will work only on multiple choise questions
import pandas as pd
import numpy as np
import plotly.express as px
df = pd.read_csv("kaggle_survey_2022_responses.csv")
def plot_answers(data, question_prefix, year):
filter_columns = [col for col in data.columns if col.startswith(question_prefix)]
df = data[filter_columns]
question = df.iloc[0][0].split("?")[0]
df = df.drop(index=0, axis=0)
df.dropna(how='all', inplace=True)
t = df.stack().reset_index()[0]
series = t.value_counts().sort_values()
num_questions = len(filter_columns)
num_rows = len(df)
labels = [f"{v} ({(v/num_rows)*100:.2f}%)" for v in series]
fig = px.bar(series,
labels={"": '',"value": ""},
text=labels,
orientation="h",)
fig.update_layout(showlegend=False,
title={'text': f'{question} in {year}',
'y':0.95,
'x':0.5,},
xaxis_range=[0,series[-1]*1.1])
fig.write_image(f'{question_prefix}_{year}.png')
fig.show()
# example usage for used programming languages
plot_answers(df, "Q12", 2022)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment