Python Data Analysis Part 4: Programming Languages

prog_languages.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[["LanguageWorkedWith"]]

data = data.dropna()

split_languages = data["LanguageWorkedWith"]\
    .apply(lambda languages_row: pd.Series(languages_row.split(";")))

languages = split_languages.stack()

languages = languages.reset_index()
languages.columns = ["Respondent ID", "Language Reported Order", "Languages"]

languages_counts = languages[["Languages", "Respondent ID"]]\
    .groupby(by=["Languages"])\
    .count()\
    .sort_values("Respondent ID", ascending=False)

languages_counts = languages_counts.head(n=15)

fig = px.bar(
    languages_counts, 
    title="Top 15 Most Used Programming Languages", 
)
fig.update_layout(
    xaxis_title = "Programming Language",
    yaxis_title = "Frequency",
    title_x = 0.5,
    showlegend = False
)
fig.show()