Skip to content

Instantly share code, notes, and snippets.

@Ze1598
Last active May 4, 2020 15:26
Show Gist options
  • Save Ze1598/58b3af548e2429488213f698dc62e769 to your computer and use it in GitHub Desktop.
Save Ze1598/58b3af548e2429488213f698dc62e769 to your computer and use it in GitHub Desktop.
Bin data using custom intervals with pandas (integers)
import pandas as pd
import numpy as np
import plotly.express as px
from typing import List, Union
def bin_ages(age_series: pd.Series) -> pd.Series:
age_labels = [f"[{i}, {i+10})" for i in range(0, 91, 10)]
age_bins = pd.IntervalIndex.from_tuples(
[(i, i+10) for i in range(0, 91, 10)],
closed="left"
)
ages_binned = pd.cut(
age_series,
age_bins,
labels=age_labels,
precision=0,
include_lowest=True
)
ages_binned.sort_values(ascending=True, inplace=True)
# Change the values from categorical to string to be able to plot them
ages_binned = ages_binned.astype("str")
return ages_binned
def plot_histogram(
data_series: pd.Series,
nbins: int,
title: str,
axes_titles: List[Union[str, None]]
) -> None:
fig = px.histogram(
x=data_series,
nbins=nbins,
title=title
)
fig.update_layout(
xaxis_title=axes_titles[0],
yaxis_title=axes_titles[1]
)
fig.update_layout(
uniformtext_minsize=14,
uniformtext_mode="hide",
bargap=0,
title_x=0.5
)
fig.show()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment