Plotting Data using Matplotlib

Overview

Learning outcomes

• Students will be able to explain the purpose of data visualisation and choose a suitable chart (line, bar or histogram) for given data.
• Students will be able to draw line plots with plt.plot() and customise colour, marker, line style and line width.
• Students will be able to draw vertical, horizontal and grouped bar graphs with bar() and barh().
• Students will be able to draw histograms with hist(), choosing bins, edgecolor, histtype and cumulative, and read frequencies from them.
• Students will be able to add a title, axis labels, legend, grid and custom ticks, and set the figure size.
• Students will be able to save a chart in different formats with savefig().
• Students will be able to plot Series and DataFrames, including data read from CSV files, using df.plot(kind=...).
• Students will be able to complete, correct and predict the output of plotting code in board-style questions.

Lesson plan

Notes

import matplotlib.pyplot as plt

days = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
temp = [31, 33, 34, 32, 35, 36, 34]   # maximum temperature in Jaipur (deg C)

plt.plot(days, temp)
plt.show()

import matplotlib.pyplot as plt

tests = ['UT1', 'UT2', 'UT3', 'UT4']
riya = [68, 74, 81, 88]
kabir = [72, 70, 77, 79]

plt.plot(tests, riya, label='Riya')
plt.plot(tests, kabir, label='Kabir')
plt.title('Unit Test Marks in Informatics Practices')
plt.xlabel('Unit Test')
plt.ylabel('Marks (out of 100)')
plt.legend()
plt.grid(True)
plt.show()

import matplotlib.pyplot as plt

overs = [1, 2, 3, 4, 5, 6]
india = [8, 14, 25, 31, 42, 55]
australia = [6, 15, 21, 30, 37, 44]

plt.plot(overs, india, color='blue', marker='o', markersize=8,
         linestyle='--', linewidth=2, label='India')
plt.plot(overs, australia, 'y^:', linewidth=3, label='Australia')
plt.title('Powerplay: cumulative runs')
plt.xlabel('Over')
plt.ylabel('Runs')
plt.legend()
plt.show()

import matplotlib.pyplot as plt

month = list(range(1, 13))
rain = [1, 0, 1, 1, 11, 520, 840, 590, 340, 90, 15, 4]   # Mumbai, mm (approx.)
names = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
         'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']

plt.figure(figsize=(10, 4))
plt.plot(month, rain, color='navy', marker='s')
plt.xticks(month, names, rotation=45)
plt.yticks(range(0, 901, 100))
plt.title('Average monthly rainfall in Mumbai')
plt.xlabel('Month')
plt.ylabel('Rainfall (mm)')
plt.grid(True)
plt.show()

import matplotlib.pyplot as plt

subjects = ['English', 'Maths', 'Physics', 'Chemistry', 'IP']
average = [72, 65, 61, 68, 81]

plt.bar(subjects, average, width=0.6,
        color=['tomato', 'orange', 'gold', 'yellowgreen', 'skyblue'],
        edgecolor='black')
plt.title('Class XII-B: subject-wise average marks')
plt.xlabel('Subject')
plt.ylabel('Average marks')
plt.show()

import matplotlib.pyplot as plt

players = ['Shubman', 'Yashasvi', 'Rinku', 'Tilak', 'Hardik']
runs = [412, 375, 298, 260, 214]

plt.barh(players, runs, color='darkorange', height=0.5)
plt.title('Runs scored in the series')
plt.xlabel('Runs')
plt.ylabel('Batter')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

sections = ['XII-A', 'XII-B', 'XII-C', 'XII-D']
boys = [18, 20, 15, 17]
girls = [16, 14, 19, 18]

x = np.arange(len(sections))   # positions 0, 1, 2, 3
w = 0.35
plt.bar(x - w/2, boys, width=w, color='steelblue', label='Boys')
plt.bar(x + w/2, girls, width=w, color='hotpink', label='Girls')
plt.xticks(x, sections)
plt.title('Strength of Class XII sections')
plt.xlabel('Section')
plt.ylabel('Number of students')
plt.legend()
plt.show()

import matplotlib.pyplot as plt

marks = [45, 52, 58, 61, 63, 67, 68, 70, 72, 74,
         75, 77, 78, 81, 83, 85, 88, 90, 92, 97]

counts, edges, bars = plt.hist(marks, bins=[40, 50, 60, 70, 80, 90, 100],
                               color='skyblue', edgecolor='black')
print('Frequencies:', counts)
print('Bin edges  :', edges)
plt.title('Distribution of IP marks, Class XII-A')
plt.xlabel('Marks')
plt.ylabel('Number of students')
plt.show()

Frequencies: [1. 2. 4. 6. 4. 3.]
Bin edges  : [ 40.  50.  60.  70.  80.  90. 100.]

import matplotlib.pyplot as plt

heights = [142, 145, 147, 149, 150, 151, 152, 153, 154, 155,
           156, 156, 157, 158, 159, 160, 161, 163, 165, 168]

counts, edges, bars = plt.hist(heights, bins=[140, 145, 150, 155, 160, 165, 170],
                               cumulative=True, histtype='step',
                               color='purple', linewidth=2)
print('Cumulative counts:', counts)
plt.title('Heights of Class IX students (cumulative)')
plt.xlabel('Height (cm)')
plt.ylabel('Students up to this height')
plt.show()

Cumulative counts: [ 1.  4.  9. 15. 18. 20.]

import matplotlib.pyplot as plt

items = ['Samosa', 'Sandwich', 'Juice', 'Idli', 'Noodles']
sold = [120, 85, 60, 95, 70]

plt.bar(items, sold, color='seagreen')
plt.title('Canteen sales on Monday')
plt.xlabel('Item')
plt.ylabel('Plates sold')
plt.savefig('canteen_sales.png')
plt.savefig('canteen_sales.pdf', bbox_inches='tight')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

canteen = pd.DataFrame({
    'Month': ['Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep'],
    'Tea': [520, 480, 300, 450, 470, 510],
    'Coffee': [310, 290, 180, 260, 300, 330]
})

canteen.plot(kind='line', x='Month', y=['Tea', 'Coffee'],
             marker='o', title='Cups sold in the staff canteen')
plt.ylabel('Cups')
plt.show()

canteen.plot(kind='bar', x='Month', color=['brown', 'peru'],
             title='Tea vs Coffee (bar)')
plt.ylabel('Cups')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

result = pd.DataFrame({
    'Name': ['Aman', 'Bhavya', 'Chirag', 'Divya', 'Esha', 'Farhan', 'Gauri', 'Harsh'],
    'Total': [412, 455, 380, 470, 398, 431, 446, 365]
})

result.plot(kind='barh', x='Name', y='Total', color='slateblue',
            legend=False, title='Total marks (out of 500)')
plt.xlabel('Total marks')
plt.show()

result.plot(kind='hist', y='Total', bins=[350, 380, 410, 440, 470, 500],
            edgecolor='black', title='Distribution of totals')
plt.xlabel('Total marks')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('result.csv')
df = df.set_index('Name')
print(df.mean())

df[['English', 'Maths', 'IP']].plot(kind='bar', figsize=(9, 4),
                                    edgecolor='black')
plt.title('Marks in three subjects')
plt.ylabel('Marks')
plt.xticks(rotation=0)
plt.savefig('three_subjects.png')
plt.show()

English      79.333333
Maths        76.500000
Physics      72.333333
Chemistry    75.333333
IP           85.833333
dtype: float64

import matplotlib.pyplot as plt

transport = ['Bus', 'Walk', 'Cycle', 'Parent', 'Auto']
students = [420, 150, 110, 230, 90]
plt.pie(students, labels=transport, autopct='%1.1f%%')
plt.title('How students come to school')
plt.show()

hours = [1, 2, 2, 3, 4, 4, 5, 6, 6, 7]
score = [42, 50, 55, 58, 66, 70, 74, 80, 83, 90]
plt.scatter(hours, score, color='crimson', marker='D')
plt.title('Self-study hours vs test score')
plt.xlabel('Hours of self-study per day')
plt.ylabel('Score')
plt.show()

import pandas as pd
import matplotlib.pyplot as plt

marks = pd.DataFrame({
    'XII-A': [55, 62, 68, 70, 71, 74, 78, 81, 85, 97],
    'XII-B': [40, 58, 60, 63, 66, 67, 69, 72, 75, 79]
})
marks.plot(kind='box', title='Spread of IP marks')
plt.ylabel('Marks')
plt.show()

energy = pd.DataFrame({'Solar': [20, 35, 50, 70],
                       'Grid': [80, 70, 60, 45]},
                      index=['2022', '2023', '2024', '2025'])
energy.plot(kind='area', title='School electricity sources (units x 100)')
plt.show()

Key terms

Data visualisation

Representing data as charts or graphs so that patterns, trends and comparisons are easy to see.

Matplotlib

A Python library for creating 2D static, animated and interactive plots.

pyplot

The module of Matplotlib with simple functions such as plot(), bar(), hist() and show(); imported as plt.

Figure

The whole window or image on which one or more plots are drawn.

Line plot

A chart that joins data points with straight lines; used for trends over time.

Bar graph

A chart of rectangular bars, with gaps, whose lengths compare values of separate categories.

Histogram

A chart of touching bars showing how many values of numeric data fall in each interval.

Bin

One interval of a histogram; bins are set by the bins parameter of hist().

Frequency

The number of data values that fall in a bin.

Legend

A key on the chart that tells which colour or line stands for which data set.

Marker

A symbol (circle, star, square, ...) drawn at each data point of a line plot.

Line style

The pattern of a line: solid, dashed, dotted or dash-dot.

Tick

A small mark with a label along an axis; changed with xticks() and yticks().

figsize

A parameter giving (width, height) of a figure in inches.

savefig()

A pyplot function that saves the current figure to a file such as PNG, JPG, PDF or SVG.

kind

The parameter of pandas plot() that chooses the chart type: 'line', 'bar', 'barh', 'hist' and others.

Cumulative histogram

A histogram in which each bar counts all values up to and including that bin.

MCQs

Tap an option to check it, or use Show answers above to reveal them all.

1. Which Matplotlib module provides simple functions such as plot(), bar() and hist()?

   1. matplotlib.plot
   2. matplotlib.pyplot
   3. matplotlib.chart
   4. pandas.plotting
   Answer

   (b) matplotlib.pyplot

   pyplot is the Matplotlib module with simple plotting functions. It is usually imported as import matplotlib.pyplot as plt.

2. What does plt.xticks([0, 1, 2], ['Mon', 'Tue', 'Wed']) do?

   1. Writes 'Mon Tue Wed' as the x-axis title
   2. Draws three vertical lines
   3. Shows the labels Mon, Tue and Wed at x positions 0, 1 and 2
   4. Sets the x-axis range from 0 to 2
   Answer

   (c) Shows the labels Mon, Tue and Wed at x positions 0, 1 and 2

   The first list gives tick positions and the second gives the text shown at those positions.

3. By default, plt.plot(x, y) draws:

   1. a line joining the points
   2. vertical bars
   3. unconnected dots only
   4. a histogram
   Answer

   (a) a line joining the points

   plot() draws a line plot. Markers appear only if a marker is given.

4. Which function writes a name below the horizontal axis?

   1. title()
   2. ylabel()
   3. legend()
   4. xlabel()
   Answer

   (d) xlabel()

   xlabel() names the x-axis; ylabel() names the y-axis; title() writes the heading.

5. A program calls plt.plot(x, a) and plt.plot(x, b), then plt.legend(), but no legend appears on the chart. What is the most likely reason?

   1. The label parameter was not given in the plot() calls
   2. legend() must be called before plot()
   3. legend() works only with bar charts
   4. show() was not called
   Answer

   (a) The label parameter was not given in the plot() calls

   legend() takes its text from the label= of each plotted line. Without labels there is nothing to show.

6. The format string 'g*--' in plt.plot(x, y, 'g*--') gives:

   1. a green dotted line with plus markers
   2. a grey solid line with star markers
   3. a green dashed line with star markers
   4. a green dash-dot line with no markers
   Answer

   (c) a green dashed line with star markers

   g = green, * = star marker, -- = dashed line.

7. Which value of linestyle draws a dotted line?

   1. '-'
   2. '--'
   3. '-.'
   4. ':'
   Answer

   (d) ':'

   ':' (or 'dotted') is dotted; '-' solid, '--' dashed, '-.' dash-dot.

8. Which colour code stands for black in Matplotlib?

   1. 'b'
   2. 'k'
   3. 'bl'
   4. 'B'
   Answer

   (b) 'k'

   'k' is black. 'b' is blue.

9. Which parameter of plot() makes the line thicker?

   1. linewidth
   2. linestyle
   3. markersize
   4. width
   Answer

   (a) linewidth

   linewidth (or lw) sets the thickness of the line in points.

10. Which function draws bars from left to right, with categories on the y-axis?

    1. bar()
    2. hbar()
    3. hist()
    4. barh()
    Answer

    (d) barh()

    barh() draws a horizontal bar graph.

11. What is the default width of each bar in plt.bar()?

    1. 0.5
    2. 0.8
    3. 1.0
    4. 0.25
    Answer

    (b) 0.8

    The default width is 0.8, which leaves a gap of 0.2 between bars placed at positions 0, 1, 2, ...

12. A histogram is the most suitable chart to show:

    1. how the heights of 200 students are spread over intervals
    2. the population of five states
    3. the share of each house in total points
    4. the daily price of petrol over a month
    Answer

    (a) how the heights of 200 students are spread over intervals

    A histogram shows the distribution of continuous numeric data over intervals. State populations need a bar graph and a daily price needs a line plot.

13. plt.hist(data, bins=5) divides the data into:

    1. 5 bins of 5 units each
    2. bins of width 5
    3. 5 equal-width bins from the smallest to the largest value
    4. bins 0-5, 5-10, 10-15, 15-20 and 20-25
    Answer

    (c) 5 equal-width bins from the smallest to the largest value

    An integer bins value gives that many equal-width intervals covering the range of the data.

14. With bins=[0, 10, 20, 30], in which bin is the value 20 counted?

    1. 0-10
    2. 10-20
    3. 20-30
    4. It is not counted
    Answer

    (c) 20-30

    Each bin includes its left edge and excludes its right edge (except the last bin), so 20 goes in 20-30.

15. Which histtype draws only the outline of the histogram, without filling?

    1. 'bar'
    2. 'step'
    3. 'stepfilled'
    4. 'barstacked'
    Answer

    (b) 'step'

    'step' draws an unfilled outline. 'stepfilled' fills it.

16. If cumulative=True is passed to hist(), then:

    1. the bars are drawn horizontally
    2. each bin shows the percentage of values
    3. bins are sorted from tallest to shortest
    4. each bar shows the count of all values up to and including that bin
    Answer

    (d) each bar shows the count of all values up to and including that bin

    A cumulative histogram adds up counts, so the last bar equals the total number of values.

17. A student writes plt.show() and then plt.savefig('a.png'). The saved file is blank. Why?

    1. PNG is not supported
    2. The figure is cleared once the shown window is closed, so savefig must come first
    3. savefig needs a full path
    4. savefig works only with pandas
    Answer

    (b) The figure is cleared once the shown window is closed, so savefig must come first

    Always call savefig() before show().

18. Which file type can NOT be produced by plt.savefig()?

    1. .png
    2. .pdf
    3. .svg
    4. .docx
    Answer

    (d) .docx

    savefig supports image and vector formats such as png, jpg, pdf and svg, but not Word documents.

19. In plt.figure(figsize=(8, 4)), the numbers 8 and 4 are:

    1. rows and columns of the grid
    2. width and height in centimetres
    3. width and height in inches
    4. the x and y axis limits
    Answer

    (c) width and height in inches

    figsize is (width, height) in inches.

20. A DataFrame df has a column Month and two numeric columns, Tea and Coffee. What does df.plot(kind='bar', x='Month') draw?

    1. A grouped bar chart with one pair of bars per month and a legend for Tea and Coffee
    2. Only the Tea column
    3. A histogram of Month
    4. An error, because two columns cannot be plotted
    Answer

    (a) A grouped bar chart with one pair of bars per month and a legend for Tea and Coffee

    pandas draws one bar per numeric column for each x value and builds the legend from the column names.

Assertion–Reason

1. Assertion (A): In a histogram there are no gaps between adjacent bars.

   Reason (R): The bins of a histogram are continuous intervals; the right edge of one bin is the left edge of the next.

   Answer

   (A)

   Both are true and the continuity of bins is exactly why the bars touch.

2. Assertion (A): plt.legend() can show a separate name for each line in a multi-line plot.

   Reason (R): The legend reads the text from the label parameter of each plot() call.

   Answer

   (A)

   Both are true and R explains how legend() knows the names.

3. Assertion (A): Calling plt.savefig('x.png') after plt.show() always saves the complete chart.

   Reason (R): savefig() can save a chart in formats such as PNG, PDF and SVG.

   Answer

   (D)

   A is false: after the shown window is closed the figure is cleared and a blank image is saved. R is true.

4. Assertion (A): A bar graph is suitable for comparing the sales of different products in a shop.

   Reason (R): The bars of a bar graph must always be vertical.

   Answer

   (C)

   A is true. R is false: barh() draws horizontal bars.

5. Assertion (A): The marker parameter shows a symbol at each data point of a line plot.

   Reason (R): The linestyle parameter decides whether a line is solid, dashed or dotted.

   Answer

   (B)

   Both statements are true, but the line style has nothing to do with markers, so R does not explain A.

Short answer

1. 2 marks

   What is data visualisation? Give two reasons why we plot data.

   Answer

   Data visualisation is the graphical representation of data using charts and graphs.

   Reasons: (1) trends and patterns, such as rising or falling sales, are seen at a glance; (2) it is easier to compare values and spot errors or outliers, and to communicate results to people who will not read raw numbers.

2. 2 marks

   Give two differences between a bar graph and a histogram.

   Answer

   • A bar graph compares separate categories; a histogram shows the distribution of continuous numeric data over intervals.
   • Bars of a bar graph have gaps; bars of a histogram touch each other. (Also: bar() is given the heights, hist() counts the values itself.)
3. 2 marks

   Fill in the blanks so that the program draws a line plot of runs scored in each over, with a title and an x-axis label.

   1. import matplotlib.________ as plt
   2. overs = [1, 2, 3, 4, 5]
   3. runs = [6, 11, 4, 9, 14]
   4. plt.________(overs, runs)
   5. plt.________('Runs per over')
   6. plt.________('Over number')
   7. plt.show()
   Answer

   Blanks: pyplot, plot, title, xlabel. Complete program:

   import matplotlib.pyplot as plt
   overs = [1, 2, 3, 4, 5]
   runs = [6, 11, 4, 9, 14]
   plt.plot(overs, runs)
   plt.title('Runs per over')
   plt.xlabel('Over number')
   plt.show()

4. 2 marks

   Write a single statement to plot lists x and y as a red dashed line, 3 points thick, with circle markers, and labelled 'Sales'.

   Answer

   Either form is correct:

   import matplotlib.pyplot as plt
   x = [1, 2, 3]
   y = [5, 7, 4]
   plt.plot(x, y, color='red', linestyle='--', linewidth=3, marker='o', label='Sales')
   # or: plt.plot(x, y, 'ro--', linewidth=3, label='Sales')
   plt.show()

5. 2 marks

   What is the purpose of plt.legend()? What must the programmer do for it to show meaningful text?

   Answer

   legend() displays a key on the chart telling which colour, line or bar belongs to which data set. For it to show names, each plotting call must have a label= argument (for example plt.plot(x, y, label='2025')), or the names must be passed as a list: plt.legend(['2024', '2025']).

6. 2 marks

   Fill in the blanks to draw a histogram of the list ages with bins 10-20, 20-30, 30-40, 40-50 and 50-60, with black borders around the bars.

   plt.hist(ages, ________ = [________], ________ = 'black')

   Answer

   bins, 10, 20, 30, 40, 50, 60 and edgecolor:

   import matplotlib.pyplot as plt
   ages = [12, 18, 25, 27, 33, 38, 41, 45, 47, 52, 58]
   plt.hist(ages, bins=[10, 20, 30, 40, 50, 60], edgecolor='black')
   plt.show()

7. 2 marks

   What does plt.savefig() do? Write the statement to save the current chart as result.pdf in the folder D:/IP.

   Answer

   savefig() saves the current figure to a file; the format comes from the extension. It must be called before show().

   plt.savefig('D:/IP/result.pdf')

8. 2 marks

   Predict the number of bars and the height of each bar drawn by: plt.hist([5, 15, 25, 35, 45], bins=[0, 20, 40, 60])

   Answer

   Three bins: 0-20 has 5 and 15 (2 values), 20-40 has 25 and 35 (2 values), 40-60 has 45 (1 value). So there are 3 bars of heights 2, 2 and 1. Checking with Python:

   import matplotlib.pyplot as plt
   counts, edges, bars = plt.hist([5, 15, 25, 35, 45], bins=[0, 20, 40, 60])
   print(counts)

   Output

   [2. 2. 1.]

9. 2 marks

   A DataFrame stock has columns Item and Qty. Fill in the blanks to draw a horizontal bar chart of quantity for each item.

   stock.plot(kind=________, x=________, y='Qty')

   Answer

   'barh' and 'Item':

   import pandas as pd
   import matplotlib.pyplot as plt
   stock = pd.DataFrame({'Item': ['Pen', 'Pencil', 'Eraser'], 'Qty': [120, 300, 90]})
   stock.plot(kind='barh', x='Item', y='Qty')
   plt.show()

10. 2 marks

    Name any four parameters of plot() used to customise a line and state what each does.

    Answer

    • color: colour of the line, e.g. 'green'.
    • marker: symbol at each point, e.g. 'o', '*'.
    • linestyle: pattern of the line, e.g. '--', ':'.
    • linewidth: thickness of the line, e.g. 2.5.

    (Also accepted: markersize, label, markeredgecolor.)

11. 2 marks

    Differentiate between xlabel() and xticks() with an example of each.

    Answer

    xlabel() writes one name for the whole x-axis, e.g. plt.xlabel('Month').

    xticks() sets the positions and text of the individual tick marks along the x-axis, e.g. plt.xticks([1, 2, 3], ['Jan', 'Feb', 'Mar']).

12. 2 marks

    What is the role of the bins parameter in hist()? Explain the two ways it can be given.

    Answer

    bins decides the intervals into which the data is grouped.

    • As an integer, e.g. bins=4: four equal-width bins from the minimum to the maximum value.
    • As a list of edges, e.g. bins=[0, 33, 60, 100]: bins 0-33, 33-60 and 60-100, which may be of unequal width. Each bin includes its left edge; the last bin also includes its right edge.

Long answer

1. 3 marks

   Write a Python program to draw a bar graph showing the house-wise points of a school sports meet: Tagore 145, Raman 160, Shivaji 132, Ashoka 171. Give each bar a different colour, add a title and axis labels, and save the chart as houses.png.

   Answer

   Program (savefig comes before show):

   import matplotlib.pyplot as plt
   
   houses = ['Tagore', 'Raman', 'Shivaji', 'Ashoka']
   points = [145, 160, 132, 171]
   
   plt.bar(houses, points, color=['red', 'blue', 'green', 'gold'])
   plt.title('Annual Sports Meet: House Points')
   plt.xlabel('House')
   plt.ylabel('Points')
   plt.savefig('houses.png')
   plt.show()

2. 3 marks

   Fill in the five blanks so that the program plots the maximum temperatures of Delhi and Shimla for five days on the same chart, with markers, a legend and a grid.

   1. import matplotlib.pyplot as plt
   2. days = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri']
   3. delhi = [39, 41, 40, 42, 38]
   4. shimla = [24, 25, 23, 26, 22]
   5. plt.plot(days, delhi, marker='o', ________='Delhi')
   6. plt.plot(days, shimla, marker='s', label='Shimla')
   7. plt.________('Maximum temperature in May')
   8. plt.ylabel('Temperature (deg C)')
   9. plt.________()
   10. plt.________(True)
   11. plt.________()
   Answer

   Blanks: label, title, legend, grid, show.

   import matplotlib.pyplot as plt
   days = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri']
   delhi = [39, 41, 40, 42, 38]
   shimla = [24, 25, 23, 26, 22]
   plt.plot(days, delhi, marker='o', label='Delhi')
   plt.plot(days, shimla, marker='s', label='Shimla')
   plt.title('Maximum temperature in May')
   plt.ylabel('Temperature (deg C)')
   plt.legend()
   plt.grid(True)
   plt.show()

3. 3 marks

   Find and correct the errors in the following code. Rewrite the correct code and underline (mention) each correction.

   1. import matplotlib.pyplot as pl
   2. x = [1, 2, 3, 4]
   3. y = [10, 20, 15]
   4. plt.plot(x, y, colour='red')
   5. plt.title = 'Weekly sales'
   6. plt.show
   Answer

   Corrections: (1) alias must match its use, so as plt; (2) x and y must be the same length, so add a fourth value to y; (3) colour must be color; (4) title is a function, so plt.title('Weekly sales'); (5) show must be called with brackets: plt.show().

   import matplotlib.pyplot as plt
   x = [1, 2, 3, 4]
   y = [10, 20, 15, 25]
   plt.plot(x, y, color='red')
   plt.title('Weekly sales')
   plt.show()

4. 3 marks

   Explain the histtype and cumulative parameters of hist(). Write code that draws a cumulative, outline-only histogram of the list wt = [38, 41, 44, 45, 47, 49, 50, 52, 55, 58] using bins 35-40-45-50-55-60, and print the cumulative counts.

   Answer

   histtype sets the drawing style: 'bar' (filled bars, default), 'barstacked' (stacked bars for several data sets), 'step' (outline only) and 'stepfilled' (filled outline). cumulative=True makes each bar count all values up to and including that bin, so the last bar equals the number of values.

   Bins: 35-40 has 38 (1); 40-45 has 41, 44 (2); 45-50 has 45, 47, 49 (3); 50-55 has 50, 52 (2); 55-60 has 55, 58 (2). Cumulative counts: 1, 3, 6, 8, 10.

   import matplotlib.pyplot as plt
   wt = [38, 41, 44, 45, 47, 49, 50, 52, 55, 58]
   c, e, b = plt.hist(wt, bins=[35, 40, 45, 50, 55, 60],
                      histtype='step', cumulative=True)
   print(c)
   plt.title('Weights of students (cumulative)')
   plt.xlabel('Weight (kg)')
   plt.ylabel('Number of students')
   plt.show()

   Output

   [ 1.  3.  6.  8. 10.]

5. 5 marks

   The file sales.csv contains quarterly sales (in lakh rupees) of a company's North and South regions, with columns Region, Quarter and Sales.

   Write a program to (a) read the file into a DataFrame, (b) arrange it so that each quarter is a row and each region a column, (c) draw a grouped bar chart with a title, axis labels and legend, and (d) save the chart as quarterly.png. Also print the total sales of each region.

   Answer

   pivot() turns the long table into one row per quarter and one column per region. df.plot(kind='bar') then draws a pair of bars per quarter, and the legend is built from the column names North and South.

   import pandas as pd
   import matplotlib.pyplot as plt
   
   df = pd.read_csv('sales.csv')
   table = df.pivot(index='Quarter', columns='Region', values='Sales')
   print(table.sum())
   
   table.plot(kind='bar', color=['teal', 'coral'], edgecolor='black')
   plt.title('Quarterly sales by region')
   plt.xlabel('Quarter')
   plt.ylabel('Sales (Rs lakh)')
   plt.xticks(rotation=0)
   plt.legend(title='Region')
   plt.savefig('quarterly.png')
   plt.show()

   Output

   Region
   North    1780
   South    1710
   dtype: int64

6. 5 marks

   Compare a line plot, a bar graph and a histogram: say when each is used and write one short pyplot statement for each. Then, for each situation below, name the best chart: (i) monthly electricity bill of a school for a year, (ii) number of medals won by five states, (iii) waiting times of 300 patients at a hospital.

   Answer

   • Line plot: shows change over time or ordered data; points are joined. plt.plot(months, bill)
   • Bar graph: compares separate categories; bars with gaps. plt.bar(states, medals)
   • Histogram: shows how numeric data is spread over intervals; bars touch and heights are frequencies. plt.hist(waiting, bins=10)

   (i) Line plot, because the bill changes over time. (ii) Bar graph, because states are separate categories. (iii) Histogram, because waiting time is continuous data and we want its distribution.

7. 5 marks

   Write a program that creates a DataFrame of five students (Name, Term1, Term2 marks out of 100), then draws (a) a line chart of both terms with markers and (b) a horizontal bar chart of Term2 marks, both from the DataFrame using plot(kind=...). Add suitable titles and axis labels.

   Answer

   One possible program:

   import pandas as pd
   import matplotlib.pyplot as plt
   
   df = pd.DataFrame({
       'Name': ['Arjun', 'Pooja', 'Kunal', 'Neha', 'Vikram'],
       'Term1': [72, 85, 64, 90, 58],
       'Term2': [78, 88, 70, 86, 66]
   })
   
   df.plot(kind='line', x='Name', y=['Term1', 'Term2'], marker='o',
           title='Term-wise marks')
   plt.ylabel('Marks')
   plt.show()
   
   df.plot(kind='barh', x='Name', y='Term2', color='olive',
           legend=False, title='Term 2 marks')
   plt.xlabel('Marks')
   plt.show()

Case-based

Practicals

import pandas as pd
import matplotlib.pyplot as plt

marks = pd.DataFrame({
    'Ananya': [88, 92, 79, 85, 95],
    'Bharat': [72, 65, 70, 68, 81],
    'Charu': [91, 78, 84, 80, 87],
    'Dev': [60, 74, 66, 71, 77]
}, index=['English', 'Maths', 'Physics', 'Chemistry', 'IP'])
print(marks)

styles = ['o', 's', '^', 'D']
for name, m in zip(marks.columns, styles):
    plt.plot(marks.index, marks[name], marker=m, label=name)
plt.title('Subject-wise marks of four students')
plt.xlabel('Subject')
plt.ylabel('Marks')
plt.legend()
plt.grid(True)
plt.show()

           Ananya  Bharat  Charu  Dev
English        88      72     91   60
Maths          92      65     78   74
Physics        79      70     84   66
Chemistry      85      68     80   71
IP             95      81     87   77

import matplotlib.pyplot as plt

sec = ['XII-A', 'XII-B', 'XII-C', 'XII-D', 'XII-E']
avg = [74, 68, 81, 77, 63]

plt.bar(sec, avg, width=0.5, edgecolor='black',
        color=['#4e79a7', '#f28e2b', '#59a14f', '#e15759', '#b07aa1'])
plt.title('Section-wise average in IP')
plt.xlabel('Section')
plt.ylabel('Average marks')
plt.savefig('section_avg.png')
plt.savefig('section_avg.pdf')
plt.show()

import matplotlib.pyplot as plt
import numpy as np

subjects = ['English', 'Maths', 'Physics', 'Chemistry', 'IP']
term1 = [70, 62, 58, 66, 78]
term2 = [74, 69, 63, 65, 84]

x = np.arange(len(subjects))
w = 0.4
plt.bar(x - w/2, term1, width=w, label='Term 1')
plt.bar(x + w/2, term2, width=w, label='Term 2')
plt.xticks(x, subjects)
plt.title('Class average: Term 1 vs Term 2')
plt.ylabel('Average marks')
plt.legend()
plt.show()

for s, a, b in zip(subjects, term1, term2):
    print(f'{s:10s} change: {b - a:+d}')

English    change: +4
Maths      change: +7
Physics    change: +5
Chemistry  change: -1
IP         change: +6

import matplotlib.pyplot as plt

marks = [12, 18, 22, 25, 27, 28, 30, 31, 31, 33, 34, 35, 36,
         37, 38, 38, 40, 41, 42, 43, 44, 46, 47, 49, 50]
edges = [0, 10, 20, 30, 40, 50]

freq, b, p = plt.hist(marks, bins=edges, color='skyblue', edgecolor='black')
plt.title('IP unit test marks')
plt.xlabel('Marks (out of 50)')
plt.ylabel('Number of students')
plt.show()

for i in range(len(freq)):
    print(f'{edges[i]}-{edges[i+1]}: {int(freq[i])}')

plt.hist(marks, bins=edges, cumulative=True, histtype='step', linewidth=2)
plt.title('Cumulative frequency')
plt.xlabel('Marks (out of 50)')
plt.ylabel('Students up to this mark')
plt.show()

0-10: 0
10-20: 2
20-30: 4
30-40: 10
40-50: 9

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('sales.csv')
by_region = df.groupby('Region')['Sales'].sum()
by_quarter = df.groupby('Quarter')['Sales'].sum()
print(by_region)
print(by_quarter)

by_region.plot(kind='barh', color='darkcyan', title='Total sales by region')
plt.xlabel('Sales (Rs lakh)')
plt.show()

by_quarter.plot(kind='line', marker='o', color='maroon', title='Total sales by quarter')
plt.ylabel('Sales (Rs lakh)')
plt.show()

Region
North    1780
South    1710
Name: Sales, dtype: int64
Quarter
Q1    800
Q2    870
Q3    840
Q4    980
Name: Sales, dtype: int64

import pandas as pd
import matplotlib.pyplot as plt

aqi = pd.DataFrame({
    'Delhi': [312, 290, 335, 360, 298, 275, 320],
    'Chennai': [72, 85, 64, 90, 78, 69, 81]
}, index=['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'])
print(aqi.describe().loc[['mean', 'min', 'max']])

aqi.plot(kind='line', marker='o', figsize=(9, 4), title='Daily AQI')
plt.ylabel('AQI')
plt.show()

aqi.plot(kind='bar', title='Daily AQI (bar)')
plt.ylabel('AQI')
plt.xticks(rotation=0)
plt.show()

aqi.plot(kind='hist', y='Delhi', bins=4, edgecolor='black', title='Delhi AQI spread')
plt.xlabel('AQI')
plt.show()

           Delhi  Chennai
mean  312.857143     77.0
min   275.000000     64.0
max   360.000000     90.0

Common mistakes

• Writing plt.savefig() after plt.show(). The figure is cleared when the window closes, so the saved file is blank. Always save first, then show.

• Using colour= (British spelling) as a parameter. Matplotlib accepts only color= (or c=) and raises an error for colour.

• Calling plt.legend() without giving label= to any plot. No legend is drawn and Matplotlib prints a warning (No artists with labels found to put in legend). Give each plot()/bar() a label, or pass a list of names to legend().

• Passing counts to hist() instead of raw data, for example plt.hist([5, 8, 3]) meaning "5 students, 8 students, 3 students". hist() counts the values itself; for ready-made counts use bar().

• Drawing a grouped bar chart with the same x positions for both bar() calls, so one set of bars hides the other. Shift the positions by the bar width.

• Assigning instead of calling: plt.title = 'Sales' replaces the function and no title appears. Write plt.title('Sales').

• Lists of different lengths in plt.plot(x, y). Python raises a ValueError; x and y must have the same number of values.

• Confusing 'b' (blue) with black, which is 'k', and confusing xlabel() (axis name) with xticks() (labels on each tick).