Mastering Data Visualization Techniques

(Part 1)
Prepared by: Syed Afroz Ali
plt.figure(figsize = (8, 6))
plt.ticklabel_format(style = 'plain')
sns.barplot(x = heart["ChestPainType"], y = heart["Cholest
erol"], palette = "tab20");

sns.catplot(data = titanic , x ="Embarked" , y ="Age" , col

="Survived" , kind="bar" , ci =None)
plt.show()

wine.plot(kind='density', subplots=True, layout=(4,3), shar

ex=False, figsize= (14,8))
plt.show()

numeric_feature = titanic.dtypes!=object
final_numeric_feature = titanic.columns[numeric_feature].t
olist()

titanic[final_numeric_feature].plot(kind='density', subplots
=True, layout=(1,7), sharex=False, figsize= (20,4))
plt.show()

heart["ChestPainType"].value_counts()[:3].plot.pie(figsize
= (5, 5),
autopct = '%1.0f%%')
plt.title("Pie Chart")
plt.xticks(rotation = 90)
plt.show()
plt.pie(heart['ChestPainType'].value_counts(),labels=heart[
'ChestPainType'].unique(),autopct = '%1.2f%%');

plt.figure(figsize = (6, 4))

counts = heart["ChestPainType"].value_counts()
explode = (0, 0.1, 0.2, 0.3)
colors = ['#A85CF9', '#FF4949', '#BDF2D5', '#FF06B7', '#4B
7BE5', '#FF5D5D', '#FAC213', '#37E2D5', '#6D8B74', '#E9D5
CA']
counts.plot(kind = 'pie', fontsize = 12, colors = colors, expl
ode = explode, autopct = '%1.1f%%')
plt.axis('equal')
plt.legend(labels = counts.index, loc = "best")
plt.show()
my_circle=plt.Circle( (0,0), 0.9, color='white')
plt.pie(titanic['Embarked'].value_counts()[:10].values, label
s = titanic['Embarked'].value_counts()[:10].index)
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.show()

my_circle=plt.Circle( (0,0), 0.9, color='pink')

plt.pie(titanic['Embarked'].value_counts()[:10].values, label
s = titanic['Embarked'].value_counts()[:10].index)
p=plt.gcf()
p.gca().add_artist(my_circle)
plt.show()
plt.figure(figsize = (7,4))
ax = sns.countplot(x=heart['RestingECG'])
for bars in ax.containers:
ax.bar_label(bars)
plt.title("Count of RestingECG", fontsize = 15,color='Blue');
# Visulazing the distibution of the data for every feature
plt.figure(figsize=(20, 8))

for i, column in enumerate(heart.columns, 1):

plt.subplot(2, 6, i)
heart[heart["HeartDisease"] == 0][column].hist(bins=35,
color='blue', label='Have Diabetes = NO', alpha=0.9)
heart[heart["HeartDisease"] == 1][column].hist(bins=35,
color='red', label='Have Diabetes = YES', alpha=0.5)
plt.legend()
plt.xlabel(column)

cat = ['Sex','RestingECG']

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

for indx, (column, axes) in list(enumerate(list(zip(cat,
ax.flatten())))):
sns.countplot(ax = axes, x = heart[column], hue = heart[
'ExerciseAngina'],
palette = 'magma', alpha = 0.8)

else:
[axes.set_visible(False) for axes in ax.flatten()[indx + 1:]
]
plt.tight_layout()
plt.show()
plt.figure(figsize=(11,5))
plt.gcf().text(.55, .95, "Box Plot", fontsize = 40, color='Red'
,ha='center', va='center')
sns.boxenplot(x=heart['RestingECG'] , y = heart['Cholester
ol'],palette="Set1")
plt.show()

# Facet along the columns to show a categorical variable

using "col" parameter
plt.figure(figsize=(11,5))
sns.catplot(x="ChestPainType" , y = "MaxHR", hue= "Sex",
col="RestingECG", kind="boxen",palette="Set2" , h
eight=5, aspect=1 ,data=heart)
plt.show();
plt.figure(figsize=(12,5))
params = dict(data=titanic ,x = titanic.Pclass ,y = titanic.F
are ,hue=titanic.Sex,dodge=True)
sns.stripplot(**params , size=8,jitter=0.35,palette=['#33FF
66','#FF6600','Blue'],edgecolor='black',linewidth=1)
sns.boxplot(**params ,palette=['#BDBDBD','#E0E0E0'],line
width=6)
plt.show()

# Plot a subset of variables

g = sns.PairGrid(titanic, hue='Pclass' ,x_vars=["Fare" , "Ag
e"],y_vars=["Fare" , "Age"],
height=6, aspect=1)
g = g.map_offdiag(plt.scatter , edgecolor="w", s=130)
g = g.map_diag(plt.hist , edgecolor ='w', linewidth=2)
g = g.add_legend()
plt.show()
features_mean= list(wine.columns[:6])

num_rows, num_cols = 3,2

fig, axes = plt.subplots(num_rows, num_cols, figsize=(20, 8

))
fig.tight_layout()

for index, column in enumerate(wine[features_mean].colu

mns):
i,j = (index // num_cols, index % num_cols)
g = sns.distplot(wine[column], color="m", label="%.2f"%
(wine[column].skew()), ax=axes[i,j])
g = g.legend(loc="best")
y = heart['Sex']

# Explore Age distibution

g = sns.kdeplot(heart["Age"][(y == 'M') & (heart["Age"].not
null())], color="Red", shade=True)
g = sns.kdeplot(heart["Age"][(y == 'F') & (heart["Age"].notn
ull())], ax=g, color="Blue", shade=True)
g.set_xlabel("Age")
g.set_ylabel("Frequency")
g = g.legend(["Male","Female"])
raw_df = heart [['Age', 'Sex', 'ChestPainType', 'RestingBP', 'Cholester
ol', 'FastingBS',
'RestingECG', 'MaxHR', 'ExerciseAngina', 'Oldpeak', 'ST_Slope',
'HeartDisease']]
# Function to print width of barcharts on the bars
def barw(ax):
for p in ax.patches:
val = p.get_width() #height of the bar
x = p.get_x()+ p.get_width() # x- position
y = p.get_y() + p.get_height()/2 #y-position
ax.annotate(round(val,2),(x,y))
plt.figure(figsize=(10,5))
ax0 = sns.countplot(data = heart, y ='ChestPainType', order = heart['
ChestPainType'].value_counts().index)
barw(ax0)
plt.show()

sns.set_style('white')
wine.plot(kind="scatter", x="fixed acidity", y="total sulfur
dioxide", alpha=.5,
s=wine["alcohol"], label="alcohol", figsize=(10,7),
c="chlorides", cmap=plt.get_cmap("jet"), colorbar=
True,
sharex=False)
plt.legend()
plt.show()
#Correlation with Response Variable class
X = wine.drop(['quality'], axis=1)
y = wine['quality']

X.corrwith(y).plot.bar(figsize=(16, 4), rot=90, grid=True)

plt.title('Correlation with quality',
fontsize=30,
color='Red',
font='Times New Roman')
plt.show()

import matplotlib
matplotlib.rcParams.update({'font.size': 20})
ax=heart['Sex'].value_counts().plot.pie(explode=[0.1, 0.1],autopct='
%1.2f%%',shadow=True);
ax.set_title(label = "Sex", fontsize = 40,color='DarkOrange',font='Luc
ida Calligraphy');
plt.legend(labels=['M','F'])
plt.axis('off');
matplotlib.rcParams.update({'font.size': 10})
corr = wine.corr()
mask = np.triu(np.ones_like(corr, dtype=bool))
plt.title('Correlation Analysis',
fontsize=25,
color='DarkGreen',
font='Times New Roman')
sns.heatmap(corr,
mask=mask,
annot=True,
lw=0,
linecolor='white',
cmap='viridis',
fmt="0.2f")
plt.xticks(rotation=90)
plt.yticks(rotation=0)
plt.show()
#set configuration for charts
plt.rcParams["figure.figsize"]=[20 , 5]
plt.rcParams["font.size"]=15
plt.rcParams["legend.fontsize"]="medium"
plt.rcParams["figure.titlesize"]="medium"

def plot_disribution(data , x ,color,bins ):

mean = data[x].mean()
std = data[x].std()
info=dict(data = data , x = x , color = color)
plt.subplot(1 , 3 , 1 , title =f"Ditstribution of {x} column")
sns.distplot(a=data[x] , bins = bins)
plt.xlabel(f"bins of {x}")
plt.axvline(mean , label ="mean" , color ="red")
plt.ylabel("frequency")
plt.legend(["${\sigma}$ = %d"%std , f"mean = {mean:.2f}"])
plt.title(f"histogram of {x} column")
plt.subplot(1 , 3 , 2)
sns.boxplot(**info)
plt.xlabel(f"{x}")
plt.title(f"box plot of {x} column")
plt.subplot(1 , 3 , 3)
sns.swarmplot(**info)
plt.xlabel(f"{x}")
plt.title(f"distribution of points in {x} column")
plt.suptitle(f"Distribution of {x} column" , fontsize =15 , color="red
")
plt.show()

age_bins = np.arange(29 , 77+5 , 5)

base_color = sns.color_palette()[4]
plot_disribution(data = heart , x ="Age" , color = base_color , bins=ag
e_bins)
sns.set_style("white")
sns.set_context("poster",font_scale = .7)
palette = ["#1d7874","#679289","#f4c095","#ee2e31","#ffb563","#91
8450","#f85e00","#a41623","#9a031e","#d6d6d6","#ffee32","#ffd100
","#333533","#202020"]
# sns.palplot(sns.color_palette(palette))
# plt.show()

plt.subplots(figsize=(20,8))
p = sns.barplot(x=heart["ChestPainType"][:14],y=heart["Age"],palett
e=palette, saturation=1, edgecolor = "#1c1c1c", linewidth = 2)
p.axes.set_title("\n ChestPainType \n", fontsize=25)
plt.ylabel("Total Member" , fontsize = 20)
plt.xlabel("\n Name" , fontsize = 20)
# plt.yscale("log")
plt.xticks(rotation = 90)
for container in p.containers:
p.bar_label(container,label_type = "center",padding = 6,size = 15,c
olor = "black",rotation = 90,
bbox={"boxstyle": "round", "pad": 0.6, "facecolor": "orange", "edg
ecolor": "black", "alpha": 1})

sns.despine(left=True, bottom=True)
plt.show()
fig,axis=plt.subplots(ncols=4,nrows=3,figsize=(15,10))
index=0
axis=axis.flatten()

for col,values in wine.items():

sns.boxplot(y=col,data=wine,color='r',ax=axis[index])
index+=1
plt.tight_layout(pad=0.5,w_pad=0.7,h_pad=5.0);

#checking the target variables for distribution

sns.distplot(heart['Cholesterol'],color='Brown')
plt.axvline(x=heart['Cholesterol'].mean(), color='Brown', lin
estyle='--', linewidth=2)
plt.title('Cholesterol');
s = sns.countplot(x = 'quality',data = wine)
sizes=[]
for p in s.patches:
height = p.get_height()
sizes.append(height)
s.text(p.get_x()+p.get_width()/2.,
height + 3,
'{:1.2f}%'.format(height/len(wine)*100),
ha="center", fontsize=14)

countfeature = ["Survived", "Pclass", "Sex", "SibSp", "Parc

h", "Embarked"]
countlist = list(enumerate(countfeature))

plt.figure(figsize = (20,10))
plt.suptitle("Countplot of Categorical Features", fontsize=1
8)
for i in countlist:
plt.subplot(2,3,i[0]+1)
sns.countplot(data = titanic, x = i[1], hue = "Survived", p
alette="rainbow")
plt.ylabel("")
plt.legend(['Not Survived', 'Survived'], loc='upper center'
, prop={'size': 10})
plt.tight_layout()
plt.show()
numfeature = ["Age", "Fare"]
enumfeat = list(enumerate(numfeature))

plt.figure(figsize=(20,7))
plt.suptitle("Distribution and Outliers of Numerical Data", fontsize=2
0)
for i in enumfeat:
plt.subplot(1,4,i[0]+1)
sns.boxplot(data = titanic[i[1]], palette="rainbow")
plt.xlabel(str(i[1]))
for i in enumfeat:
plt.subplot(1,4,i[0]+3)
sns.histplot(data = titanic[i[1]], palette="rainbow", bins=15)
plt.xlabel(str(i[1]))
plt.tight_layout()
plt.show()
plt.figure(figsize=(20,6))
plt.title("Correlation of quality column with Independent Features", f
ontsize=15)
corr = wine.corr()["quality"].sort_values(ascending=False)[1:]
sns.barplot(x=corr.index, y=corr, color=(0.90,0.30,0.50))
plt.tight_layout()
plt.xticks(rotation = 90)
plt.show()

plt.figure(figsize=(15,5))
plt.suptitle("Probability Distribution of numerical columns
according to number of Survived", fontsize = 20)
for i in enumfeat:
plt.subplot(1,2,i[0]+1)
sns.kdeplot(data=titanic, x=i[1], hue="Survived")
plt.tight_layout()

plt.show()
import missingno as msno
msno.matrix(titanic, color=(0.50,0.30,0.80))
plt.show()
x = titanic.isnull().sum()
for a, b in x.items():
if b > 0:
print(f"There are {b} missing values in column: {a}")