How to create grouped bars charts with matplotlib with data in DataFrame

Question

This is my current output: Now i want the next bars next to the already plotted bars.

My DataFrame has 3 columns: 'Block', 'Cluster', and 'District'.

'Block' and 'Cluster' contain the numbers for plotting and the grouping is based on the strings in 'District'.

How can I plot the other bars next to the existing bars?

df=pd.read_csv("main_ds.csv")
fig = plt.figure(figsize=(20,8))
ax = fig.add_subplot(111)
plt.xticks(rotation=90)
bwidth=0.30
indic1=ax.bar(df["District"],df["Block"], width=bwidth, color='r')
indic2=ax.bar(df["District"],df["Cluster"], width=bwidth, color='b')
ax.autoscale(tight=False)

def autolabel(rects):
    for rect in rects:
        h = rect.get_height()
        ax.text(rect.get_x()+rect.get_width()/2., 1.05*h, '%d'%int(h),
                ha='center', va='top')
autolabel(indic1)
autolabel(indic2)
plt.show()

Data:

District Block Cluster Villages Schools Decadal_Growth_Rate Literacy_Rate Male_Literacy Female_Literacy Primary ... Govt_School Pvt_School Govt_Sch_Rural Pvt_School_Rural Govt_Sch_Enroll Pvt_Sch_Enroll Govt_Sch_Enroll_Rural Pvt_Sch_Enroll_Rural Govt_Sch_Teacher Pvt_Sch_Teacher 0 Dimapur 5 30 278 494 23.2 85.4 88.1 82.5 147 ... 298 196 242 90 33478 57176 21444 18239 3701 3571 1 Kiphire 3 3 94 142 -58.4 73.1 76.5 70.4 71 ... 118 24 118 24 5947 7123 5947 7123 853 261 2 Kohima 5 5 121 290 22.7 85.6 89.3 81.6 128 ... 189 101 157 49 10116 26464 5976 8450 2068 2193 3 Longleng 2 2 37 113 -30.5 71.1 75.6 65.4 60 ... 90 23 90 23 3483 4005 3483 4005 830 293 4 Mon 5 5 139 309 -3.8 56.6 60.4 52.4 165 ... 231 78 219 58 18588 16578 17108 8665 1667 903 5 rows × 26 columns

Answer 1

Try using pandas.DataFrame.plot

import pandas as pd
import numpy as np
from io import StringIO
from datetime import date
import matplotlib.pyplot as plt

def add_value_labels(ax, spacing=5):
    for rect in ax.patches:
        y_value = rect.get_height()
        x_value = rect.get_x() + rect.get_width() / 2

        space = spacing
        # Vertical alignment for positive values
        va = 'bottom'

        # If value of bar is negative: Place label below bar
        if y_value < 0:
            # Invert space to place label below
            space *= -1
            # Vertically align label at top
            va = 'top'

        # Use Y value as label and format number with one decimal place
        label = "{:.1f}".format(y_value)

        # Create annotation
        ax.annotate(
            label,                      # Use `label` as label
            (x_value, y_value),         # Place label at end of the bar
            xytext=(0, space),          # Vertically shift label by `space`
            textcoords="offset points", # Interpret `xytext` as offset in points
            ha='center',                # Horizontally center label
            va=va)                      # Vertically align label differently for
                                        # positive and negative values.

first3columns = StringIO("""District    Block   Cluster
Dimapur 5   30
Kiphire 3   3
Kohima  5   5
Longleng    2
Mon 5   5
""")

df_plot = pd.read_csv(first3columns, delim_whitespace=True)


fig, ax = plt.subplots()


#df_plot.set_index(['District'], inplace=True)
df_plot[['Block', 'Cluster']].plot.bar(ax=ax, color=['r', 'b'])
ax.set_xticklabels(df_plot['District'])

add_value_labels(ax)

plt.show()

Answer 2

Try changing

indic1=ax.bar(df["District"],df["Block"], width=bwidth, color='r')
indic2=ax.bar(df["District"],df["Cluster"], width=bwidth, color='b')

to

indic1=ax.bar(df["District"]-bwidth/2,df["Block"], width=bwidth, color='r')
indic2=ax.bar(df["District"]+bwidth/2,df["Cluster"], width=bwidth, color='b')