Loading Necessary Libraries¶

In [2]:

import matplotlib.pyplot as plt
import numpy as np
from numpy.random import randint
import pandas as pd
%matplotlib inline

Data Visualization¶

Types of Graphs covered:¶

Line Graph
- Basics
- Subplots
Bar Chart
Pie Chart
Box & Whiskers Plot

Line Graph (Basics)¶

In [5]:

x = [1, 2, 3, 8, 9, 23]
y = [5, 13, 10, 11, 45, 27]

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (10,4)

#Line 1

#Keyword Argument Notation
#plt.plot(x,y, label='2x', color='red', linewidth=2, marker='.', linestyle='--', markersize=10, markeredgecolor='blue')

#Sorthand Notation
#format = '[color][marker][line]'

plt.plot(x,y, 'g^--', label = 'A simple line', linewidth = 2)

#Line 2

# select interval we want to plot points at
x2 = np.arange(0,8.5,0.5)

# Plot part of the graph as line
plt.plot(x2[:10], x2[:10]**2, 'r', label = 'X^2') 
plt.plot(x2[9:], x2[9:]**2,  'r--')

#add title to graph
plt.title('Line Graph', loc = 'left', fontdict = {'fontname': 'Times New Roman', 'color': 'white', 'fontsize' : '22'})

#add title to axis
plt.xlabel('X-axis', fontdict = {'color': 'white', 'fontsize' : '16'})
plt.ylabel('Y-axis', fontdict = {'color': 'white', 'fontsize' : '16'})

#Ticks are the markers denoting data points on axes.
#plt.xticks([0,2,4,6,8,10,12,14,16,18,20,22,24])
#plt.yticks([5,10,15,20,25,30,35,40,45])
         
#add legend
plt.legend(loc = 0)

#save graph
plt.savefig('mygraph.png', dpi = 200)

#show graph
plt.show()

No description has been provided for this image

Multiple Plots in the same Canvas : Subplots¶

Two Plots Together¶

In [141]:

x = np.linspace(0,10,20)
x

Out[141]:

array([ 0.        ,  0.52631579,  1.05263158,  1.57894737,  2.10526316,
        2.63157895,  3.15789474,  3.68421053,  4.21052632,  4.73684211,
        5.26315789,  5.78947368,  6.31578947,  6.84210526,  7.36842105,
        7.89473684,  8.42105263,  8.94736842,  9.47368421, 10.        ])

In [142]:

y = randint(1, 50, 20)
y

Out[142]:

array([45, 29, 17, 25, 41, 48,  9, 12, 12, 39,  3,  1, 12, 47, 49, 35,  6,
       17,  1, 33])

In [6]:

x = np.linspace(0,10,20)
y = randint(1, 50, 20)

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (10,4)

# Plot 1
plt.subplot(1,2,1)
plt.plot(x, y, 'c:o')
plt.title('A Cyan Plot', fontdict = {'fontname': 'Times New Roman', 'color' : 'cyan'})
#Plot 2
plt.subplot(1,2,2)
plt.plot(x, y, 'r--_')
plt.title('A Red Plot', fontdict = {'fontname': 'Times New Roman', 'color' : 'red'})

#Title at Top
plt.suptitle('Two Plots Together', fontdict = {'fontname': 'Times New Roman', 'color': 'white'})

plt.show()

Three Plots Together¶

In [17]:

x = np.linspace(0,10,20)
y = randint(1, 50, 20)

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (12,4)

# Plot 1
plt.subplot(1,3,1)
plt.plot(x, y, 'c:o')
plt.title('A Cyan Plot', fontdict = {'fontname': 'fantasy', 'color' : 'cyan'})

#Plot 2
plt.subplot(1,3,2)
plt.plot(x, y**y, 'r--_')
plt.title('A Red Plot', fontdict = {'fontname': 'fantasy', 'color' : 'red'})

#Plot 3
plt.subplot(1,3,3)
plt.plot(x, y*x, 'g-^')
plt.title('A Green Plot', fontdict = {'fontname': 'fantasy', 'color' : 'green'})

#Labeling
plt.suptitle('Three Plots Together', fontdict = {'fontname': 'fantasy', 'color': 'white'})

plt.savefig('threeplots.png')

plt.show()

Different Methods of Creating Subplots¶

Object Oriented Method¶

In [199]:

fig = plt.figure(figsize= (10,4))

ax1 = fig.add_axes([0,0,1,1])
ax2 = fig .add_axes([0.1, 0.1, 0.4, 0.3])

ax1.plot(x, y)
ax2.plot(x, y*2)

plt.show()

Brute Force Method to plot more than one graphs¶

In [200]:

fig, ax = plt.subplots(1,2, figsize= (10,4))

ax[0].plot(x, y, 'b')
ax[1].plot(x, y*x, 'r-.')

plt.show()

For Loop Method¶

In [201]:

fig , ax = plt.subplots(1,2, figsize= (10,4))

col = ['g', 'm']
data = [y, y**y]

for i, axes in enumerate(ax):
    axes.plot(x, data[i], col[i])

fig.tight_layout()

Setting X and Y limits of subplots¶

In [162]:

fig, ax = plt.subplots(1,3, figsize = (12, 4))

#Get three plots simultaneously
ax[0].plot(x, y, x, y*x)

ax[1].plot(x, y**2, 'r')
#setting limits to y axis
ax[1].set_ylim([0,1000])

ax[2].plot(x, y, x, y*x)
#setting limits to x and y axes
ax[2].set_ylim([0,300])
ax[2].set_xlim([0,5])

plt.show()

Plotting Log(x) on a subplot¶

In [180]:

fig, ax = plt.subplots(1,2, figsize = (10,4))

ax[0].plot(x, y, x, y**2)

ax[1].plot(x, np.exp(x), 'w')
#plotting log of x
ax[1].set_yscale('log')

plt.show()

Setting Xticks and Yticks and Changing their Labels¶

In [193]:

fig, ax = plt.subplots(figsize = (10,4))

ax.plot(x, y)

ax.set_xticks([1,2,5,10])
ax.set_xticklabels([r'a', r'B', r'$\alpha$', r'$\delta$'], fontsize = 20)

ax.set_yticks([1,15,25,50])

plt.show()

Setting Y-axis Label as Scientific Notation¶

In [196]:

from matplotlib import ticker

In [198]:

fig, ax = plt.subplots(figsize = (10,4))
ax.plot(x, y)
ax.set_title('Scientific Notation')

formatter = ticker.ScalarFormatter(useMathText = True)

formatter.set_scientific(True)
formatter.set_powerlimits((-1,-1))
ax.yaxis.set_major_formatter(formatter)

plt.show()

Bar Chart (Basics)¶

In [8]:

labels = ['A', 'B', 'C']
values = [6, 8, 3]

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (10,4)

bars = plt.bar(labels, values, align = 'edge', edgecolor = 'indigo', facecolor = 'pink')

#adding title
plt.title('Bar Graph', loc = 'right', fontdict = {'fontname': 'Times New Roman', 'color': 'white', 'fontsize': '30'})

#adding label to axis 
plt.xlabel('X-axis', fontdict = {'color': 'white','fontsize' : '16'})
plt.ylabel('Y-axis', fontdict = {'color': 'white','fontsize' : '16'})
 

#add patterns to bars
bars[0].set_hatch('O')
bars[1].set_hatch('*')
bars[2].set_hatch('+')


plt.show()

Real World Examples¶

Line Chart¶

Data selected for analysis

In [6]:

gas = pd.read_csv('gas_prices.csv')

gas

Out[6]:

	Year	Australia	Canada	France	Germany	Italy	Japan	Mexico	South Korea	UK	USA
0	1990	NaN	1.87	3.63	2.65	4.59	3.16	1.00	2.05	2.82	1.16
1	1991	1.96	1.92	3.45	2.90	4.50	3.46	1.30	2.49	3.01	1.14
2	1992	1.89	1.73	3.56	3.27	4.53	3.58	1.50	2.65	3.06	1.13
3	1993	1.73	1.57	3.41	3.07	3.68	4.16	1.56	2.88	2.84	1.11
4	1994	1.84	1.45	3.59	3.52	3.70	4.36	1.48	2.87	2.99	1.11
5	1995	1.95	1.53	4.26	3.96	4.00	4.43	1.11	2.94	3.21	1.15
6	1996	2.12	1.61	4.41	3.94	4.39	3.64	1.25	3.18	3.34	1.23
7	1997	2.05	1.62	4.00	3.53	4.07	3.26	1.47	3.34	3.83	1.23
8	1998	1.63	1.38	3.87	3.34	3.84	2.82	1.49	3.04	4.06	1.06
9	1999	1.72	1.52	3.85	3.42	3.87	3.27	1.79	3.80	4.29	1.17
10	2000	1.94	1.86	3.80	3.45	3.77	3.65	2.01	4.18	4.58	1.51
11	2001	1.71	1.72	3.51	3.40	3.57	3.27	2.20	3.76	4.13	1.46
12	2002	1.76	1.69	3.62	3.67	3.74	3.15	2.24	3.84	4.16	1.36
13	2003	2.19	1.99	4.35	4.59	4.53	3.47	2.04	4.11	4.70	1.59
14	2004	2.72	2.37	4.99	5.24	5.29	3.93	2.03	4.51	5.56	1.88
15	2005	3.23	2.89	5.46	5.66	5.74	4.28	2.22	5.28	5.97	2.30
16	2006	3.54	3.26	5.88	6.03	6.10	4.47	2.31	5.92	6.36	2.59
17	2007	3.85	3.59	6.60	6.88	6.73	4.49	2.40	6.21	7.13	2.80
18	2008	4.45	4.08	7.51	7.75	7.63	5.74	2.45	5.83	7.42	3.27

Line Chart showing changes in the prices of gas (USD/gallon)

In [7]:

#add title to graph
plt.title('Change in Gas Prices', loc = 'center', fontdict = {'fontname': 'century','color': 'white', 'fontsize': '25'})

#changing style of the graph
plt.style.use('dark_background')

#add title to axislightblue
plt.xlabel('Change over Years', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '17'})
plt.ylabel('Prices (USD/Gallon)', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '17'})

#plotting all countries in the graph 
for country in gas:
    if country != 'Year':
        plt.plot(gas.Year, gas[country], marker = '.') 

plt.xticks(gas.Year[::2])
#[::2] allows to have two years ga in the xticks

#adding legend
plt.legend(['Australia', 'Canada', 'France', 'Germany', 'Italy', 'Japan', 'Mexico', 'South Korea', 'UK', 'USA'], loc = 0, bbox_to_anchor=(1,1))
#bbox_to_anchor=(1,1) puts the legend outside the graph

plt.savefig('gas_prices.png', dpi= 300, bbox_inches='tight')
#bbox_inches='tight' prevents the graph from getting cropped

plt.show()

Line Chart showing changes in the prices of gas (USD/gallon) in USA, Italy , France and Germany only

In [8]:

#add title to graph
plt.title('Change in Gas Prices', loc = 'center', fontdict = {'fontname': 'century', 'color': 'white', 'fontsize': '25'})

#changing style of the graph
plt.style.use('dark_background')

#add title to axis
plt.xlabel('Change over Years', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '17'})
plt.ylabel('Prices (USD/Gallon)', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '17'})

#Method 1

# plt.plot(gas.Year, gas.USA, 'b.--')
# plt.plot(gas.Year, gas.Canada, 'r.-')
# plt.plot(gas.Year, gas.France, 'y.:')
# plt.plot(gas.Year, gas.Germany, 'g.:')

#Method 2

specific_countries = ['USA', 'France', 'Germany', 'Italy']

for country in gas:
    plt.plot(gas.Year, gas[specific_countries], marker = '.') 

#adding blank year in the graph and customizing xticks
plt.xticks(gas.Year[::2].tolist()+[2010])

#adding legend
plt.legend(['USA', 'France', 'Germany', 'Italy'], loc = 0, bbox_to_anchor=(1,1))

plt.savefig('gas_prices_specific.png', dpi= 300, facecolor = 'white', bbox_inches='tight')

plt.show()

Histogram¶

Data selected for Analysis

In [10]:

fifa = pd.read_csv('fifa_data.csv')

fifa.head()

Out[10]:

	Unnamed: 0	ID	Name	Age	Photo	Nationality	Flag	Overall	Potential	Club	...	Composure	Marking	StandingTackle	SlidingTackle	GKDiving	GKHandling	GKKicking	GKPositioning	GKReflexes	Release Clause
0	0	158023	L. Messi	31	https://cdn.sofifa.org/players/4/19/158023.png	Argentina	https://cdn.sofifa.org/flags/52.png	94	94	FC Barcelona	...	96.0	33.0	28.0	26.0	6.0	11.0	15.0	14.0	8.0	€226.5M
1	1	20801	Cristiano Ronaldo	33	https://cdn.sofifa.org/players/4/19/20801.png	Portugal	https://cdn.sofifa.org/flags/38.png	94	94	Juventus	...	95.0	28.0	31.0	23.0	7.0	11.0	15.0	14.0	11.0	€127.1M
2	2	190871	Neymar Jr	26	https://cdn.sofifa.org/players/4/19/190871.png	Brazil	https://cdn.sofifa.org/flags/54.png	92	93	Paris Saint-Germain	...	94.0	27.0	24.0	33.0	9.0	9.0	15.0	15.0	11.0	€228.1M
3	3	193080	De Gea	27	https://cdn.sofifa.org/players/4/19/193080.png	Spain	https://cdn.sofifa.org/flags/45.png	91	93	Manchester United	...	68.0	15.0	21.0	13.0	90.0	85.0	87.0	88.0	94.0	€138.6M
4	4	192985	K. De Bruyne	27	https://cdn.sofifa.org/players/4/19/192985.png	Belgium	https://cdn.sofifa.org/flags/7.png	91	92	Manchester City	...	88.0	68.0	58.0	51.0	15.0	13.0	5.0	10.0	13.0	€196.4M

5 rows × 89 columns

Distribution of Players Overall Skills in FIFA 2018

In [11]:

bins = [70,80,90,100]

#add title to graph
plt.title('Distribution of Players Overall Skills', loc = 'center', fontdict = {'fontname': 'century', 'color': 'white', 'fontsize': '22'})

#add title to axis
plt.xlabel('Overall Skill Points', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '15'})
plt.ylabel('Number of Players', fontdict = {'fontname': 'century', 'color': 'white','fontsize' : '15'})

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (10,4)

plt.hist(fifa.Overall, bins = bins, color = 'cyan')

plt.show()

Pie Chart¶

Preferred Foot by FIFA Players

In [13]:

fifa['Preferred Foot']

Out[13]:

0         Left
1        Right
2        Right
3        Right
4        Right
         ...  
18202    Right
18203    Right
18204    Right
18205    Right
18206    Right
Name: Preferred Foot, Length: 18207, dtype: object

In [12]:

left = fifa.loc[fifa['Preferred Foot'] == 'Left'].count()[0]
right = fifa.loc[fifa['Preferred Foot'] == 'Right'].count()[0]

labels = [right, left]

plt.pie(labels, labeldistance = 1.3, labels = labels, colors = ['crimson', 'lightcoral'], autopct= '%.2f %%')

plt.title('Preferred Foot by FIFA Players', loc = 'center', fontdict = {'fontname': 'century', 'color': 'white', 'fontsize': '20'})

plt.style.use('dark_background')

plt.rcParams['figure.figsize'] = (10,4)

plt.show()

Weight Distribution of FIFA Players

In [275]:

fifa.Weight

Out[275]:

0        159lbs
1        183lbs
2        150lbs
3        168lbs
4        154lbs
          ...  
18202    134lbs
18203    170lbs
18204    148lbs
18205    154lbs
18206    176lbs
Name: Weight, Length: 18207, dtype: object

In [14]:

fifa.Weight = [
    int(x.strip('lbs')) 
    if type(x) == str
    else 
    x for x in fifa.Weight
]

fifa.Weight

Out[14]:

0        159.0
1        183.0
2        150.0
3        168.0
4        154.0
         ...  
18202    134.0
18203    170.0
18204    148.0
18205    154.0
18206    176.0
Name: Weight, Length: 18207, dtype: float64

In [15]:

plt.style.use('seaborn-ticks')

light = fifa.loc[fifa.Weight < 125].count()[0]
light_medium = fifa[(fifa.Weight >= 125) & (fifa.Weight < 150)].count()[0]
medium = fifa[(fifa.Weight >= 150) & (fifa.Weight < 175)].count()[0]
medium_heavy = fifa[(fifa.Weight >= 175) & (fifa.Weight < 200)].count()[0]
heavy = fifa[fifa.Weight >= 200].count()[0]

weights = [light,light_medium, medium, medium_heavy, heavy]
label = ['under 125', '125-150', '150-175', '175-200', 'over 200']
explode = (.3,.2,0,0,.3)

plt.title('Weight of Professional Soccer Players (lbs)',  loc = 'center', fontdict = {'fontname': 'century', 'color': 'navy', 'fontsize': '20'})

plt.pie(weights, labeldistance = 1.3, wedgeprops = {'linewidth': 5}, labels=label, explode=explode, pctdistance=0.9, autopct='%.2f %%')

plt.rcParams['figure.figsize'] = (10,4)

plt.show()

Box and Whiskers Chart¶

Comparing FIFA teams with one another

In [18]:

plt.style.use('dark_background')
plt.figure(figsize = (6,8))

barcelona = fifa.loc[fifa.Club == 'FC Barcelona']['Overall']
madrid = fifa.loc[fifa.Club == 'Real Madrid']['Overall']
juventus = fifa.loc[fifa.Club == 'Juventus']['Overall']
manchester = fifa.loc[fifa.Club == 'Manchester United']['Overall']

plt.title('FIFA Football Teams Comparison',  loc = 'center', fontdict = {'fontname': 'century', 'color': 'white', 'fontsize': '20'})

plt.boxplot([barcelona, madrid, juventus, manchester], labels = ['FC Barcelona', 'Real Madrid', 'Juventus', 'Manchester United'])

plt.show()