DataStory - Matplot&Seaborn

import seaborn as sns
import matplotlib.pyplot as plt
# Create the barplot (default estimator is np.mean)
ax=sns.barplot(x='day', y='total_bill', data=df, palette='tab10', estimator=np.sum)
# np.mean-საშუალო np.sum - ჯამი
# Annotate each bar with the mean total_bill values
for p in ax.patches:
ax.annotate(format(p.get_height(), '.2f'),
(p.get_x() + p.get_width() / 2., p.get_height()),
ha = 'center', va = 'center',
xytext =(0,-50),
textcoords = 'offset points')
# Show the plot
plt.show()

plt.figure(figsize=(7,5))
# Create a correlation matrix
corr = df_3.corr()
# Plot heatmap
sns.heatmap(corr, annot=True, cmap="coolwarm", linewidths=0.5)
plt.show()

def plot_hist(feature):
fig, ax = plt.subplots(2, 1, figsize=(10, 7))
sns.histplot(data=df_6[feature], kde=True, ax=ax[0], color="Brown")
# Calculate statistics
mean_val = df_6[feature].mean()
median_val = df_6[feature].median()
mode_val = df_6[feature].mode()[0] # Get the first mode value if multiple
# Plot mean, median, and mode
ax[0].axvline(x=mean_val, color='r', linestyle='--', linewidth=2, label=f'Mean: {round(mean_val, 3)}')
ax[0].axvline(x=median_val, color='orange', linewidth=2, label=f'Median: {round(median_val, 3)}')
ax[0].axvline(x=mode_val, color='yellow', linewidth=2, label=f'Mode: {mode_val}')
ax[0].legend()
# Plot boxplot
sns.boxplot(x=df_6[feature], ax=ax[1], color="Brown")
plt.show()
plot_hist('Age')

g = sns.catplot(x='output', col='sex', kind='count', data=df_3, palette="Dark2")
# Iterate through each subplot and add annotations
for ax in g.axes.flat:
for p in ax.patches:
# Get the height of each bar and place text on top
ax.text(p.get_x() + p.get_width() / 2, # X coordinate
p.get_height(), # Y coordinate (bar height)
int(p.get_height()), # Text to display (count value)
ha="center", va="center",
# Center the text horizontally and vertically
fontsize=10, color="black", # Customize text appearance
fontweight="bold") # Make the text bold
plt.show()

plt.violinplot([df_3["oldpeak"], df_3['slp'],df_3['thall']],
positions=[1,2,3], showmeans=True)

bar = sns.distplot(df_3["age"],color='Blue',kde=True,bins=25)
bar.legend(["Skewness: {:.2f}".format(df_3['age'].skew())])
plt.title("Age Distribution")

# Fix the column selection by using a list instead of a tuple
df_6.groupby("Sex")[["Age", "Fare", "Pclass"]].mean().plot(kind='bar')

color = plt.cm.copper(np.linspace(0, 1, 10))
df_6.groupby(['Embarked','Sex'])['Age'].count().plot(
kind='bar',
width=.4,color='gold')

sns.displot(data= df_6,x="Age", kde=True,bins = 100,
color ="red",facecolor = "#3F7F7F",
height = 5,aspect = 3.5)

fig = sns.FacetGrid(df_3, hue="output", aspect=4)
fig.map(sns.kdeplot, 'age', shade=True)
oldest = df_3['age'].max()
fig.set(xlim=(0, oldest))
fig.add_legend()
plt.show()

pd.crosstab(df_6 ['Sex'], df_6 ['Embarked']).plot(kind='bar', stacked=True)

fplt.figure(figsize=(12,6))
print("Skewness: %f" % df_6 ['Fare'].skew())
print("Kurtosis: %f" % df_6 ['Fare'].kurt())
sns.distplot(df['Fare'],bins=50,hist_kws={"edgecolor": (1,0,0,1)})
plt.show()

plt.figure(figsize=(10,5))
a=df['total_bill']
mean=a.mean()
median=np.median(a)
mode=a.mode()
sns.distplot(a,hist=False)
plt.axvline(mean,color='r',label='mean')
plt.axvline(median,color='b',label='median')
plt.axvline(mode[0],color='g',label='mode')
plt.legend()
plt.show()

g = sns.FacetGrid(df_3, col="cp")
g = g.map(plt.hist, "age")

cat = ['Sex','Embarked']
sns.set_theme(rc = {'figure.dpi': 100, 'axes.labelsize': 12,'axes.facecolor': '#f0eee9', 'grid.color': '#fffdfa','figure.facecolor': '#e8e6e1'}, font_scale = 1.2)
fig, ax = plt.subplots(5, 2, figsize = (12, 22))
for indx, (column, axes) in list(enumerate(list(zip(cat,ax.flatten())))):
sns.countplot(ax = axes, x = df_6[column], hue = df_6['Pclass'],palette = 'magma', alpha = 0.8)
else:
[axes.set_visible(False) for axes in ax.flatten()[indx + 1:]]
plt.tight_layout()
plt.show()

raw_df = df_7 [['name', 'year', 'selling_price', 'km_driven', 'fuel','seller_type','transmission', 'owner']]
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 = raw_df, y ='owner', order =
raw_df['owner'].value_counts().index)
barw(ax0)
plt.show()

X = df_3.drop(['output'], axis=1)
y = df_3['output']
X.corrwith(y).plot.bar(figsize=(16, 4), rot=90, grid=False)
plt.title('Correlation with heart', fontsize=25, color='Blue', font='Times New Roman')
plt.show()

import matplotlib
matplotlib.rcParams.update({'font.size': 12})
corr = df_3.corr()
mask = np.triu(np.ones_like(corr, dtype=bool))
# Adjust figure size
plt.figure(figsize=(10, 8), dpi=100)
plt.title('Correlation Analysis',
fontsize=18, # Increase title font size
color='Blue',
font='Lucida Calligraphy')
sns.heatmap(corr,
mask=mask,
annot=True,
lw=0,
linecolor='white',
cmap='viridis',
fmt=".2f")

# Increase font size of x-axis labels
plt.xticks(rotation=90, fontsize=12)
# Increase font size of y-axis labels
plt.yticks(rotation=0, fontsize=12)
plt.show()

corr_mat_train = df_5[['Wine', 'Alcohol', 'Malic.acid', 'Ash', 'Acl', 'Mg', 'Phenols','Flavanoids', 'Proanth', 'Color.int', 'Hue','OD', 'Proline']].corr()
threshold = 0.7
corr_threshold_train = corr_mat_train[(corr_mat_train > threshold) | (corr_mat_train< -threshold)]
plt.figure(figsize = (8, 6))
sns.heatmap(corr_threshold_train, annot = True, cmap = 'seismic', fmt = ".2f",
linewidths = 0.5, cbar_kws={'shrink': .5},annot_kws={'size': 8}).set_title('Correlations Among Features (in Train)')

import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline

def missing_values(data, thresh = 20, color = 'black', edgecolor = 'black', height = 3, width = 15):
plt.figure(figsize = (width, height))
percentage = (data.isnull().mean()) * 100
percentage.sort_values(ascending = False).plot.bar(color = color,edgecolor = edgecolor)
plt.axhline(y = thresh, color = 'r', linestyle = '-')
plt.title('Missing values percentage per column', fontsize = 15, weight ='bold' )
plt.text(len(data.isnull().sum()/len(data))/1.7, thresh + 12.5, f'Columnswith more than {thresh}% missing values', fontsize = 12, color = 'crimson',ha = 'left' ,va = 'top')
plt.text(len(data.isnull().sum()/len(data))/1.7, thresh - 5, f'Columns with less than {thresh}% missing values', fontsize=12, color='green', ha = 'left' ,va = 'top')
plt.xlabel('Columns', size = 5, weight = 'bold')
plt.ylabel('Missing values percentage')
plt.yticks(weight = 'bold')
return plt.show()

missing_values(df_6, thresh = 10, color = sns.color_palette('Reds',15))

NUMERICAL = df_5[['Alcohol', 'Malic.acid', 'Ash', 'Acl', 'Mg', 'Phenols']]
fig, axes = plt.subplots(2, 4)
fig.set_figheight(15)
fig.set_figwidth(20)

for i,col in enumerate(NUMERICAL):
sns.histplot(df_5[col],ax=axes[(i // 4) -1 ,(i % 4)], kde = True)
axes[(i // 4) -1 ,(i % 4)].axvline(df_5[col].mean(), color='k', linestyle='dashed', linewidth=1)

matplotlib.rcParams.update({'font.size': 15})
ax=df_3['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='LucidaCalligraphy');
plt.legend(labels=['M','F'])
plt.axis('off')

#set configuration for charts
plt.rcParams["figure.figsize"]=[18 , 7]
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 =20 , color="red")

plt.show()
age_bins = np.arange(29 , 77+5 , 5)
base_color = sns.color_palette()[4]
plot_disribution(data = df_3 , x ="age" , color = base_color ,bins=age_bins)

sns.set_style("white")
sns.set_context("poster",font_scale = 1.2)

palette =["#1d7874","#679289","#f4c095","#ee2e31","#ffb563","#918450","#f85e00","#a41623","#9a031e","#d6d6d6","#ffee32","#ffd100","#333533","#202020"]

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

p = sns.barplot(
x=df_6["Pclass"][:14],
y=df_6["Age"],
palette=palette,
saturation=1,
edgecolor = "#1c1c1c",
linewidth = 2)

p.axes.set_title("\nTop Anime Community\n", fontsize=25)
plt.ylabel("Total Member" , fontsize = 10)
plt.xlabel("\nAnime Name" , fontsize = 10)
plt.xticks(rotation = 90)

for container in p.containers:

p.bar_label(
container,
label_type = "center",
padding = 6,
size = 10,
color ="black",
rotation = 90,
bbox={"boxstyle": "round", "pad": 0.6, "facecolor": "orange", "edgecolor":"black", "alpha": 1})

sns.despine(left=True, bottom=True)

plt.show()

countfeature = ["Survived", "Pclass", "Sex"]
countlist = list(enumerate(countfeature))
plt.figure(figsize = (15,10))
plt.suptitle("Countplot of Categorical Features", fontsize=5,color='Red')

for i in countlist:
plt.subplot(2,3,i[0]+1)
sns.countplot(data = df_6, x = i[1], hue = "Survived",palette="rainbow")
plt.ylabel("")
plt.legend(['Not Survived', 'Survived'], loc='upper center', prop={'size':1}) plt.tight_layout()
plt.show()

plt.figure(figsize=(12, 8))
# Calculate correlation and sort values
data = df_6.select_dtypes(include="number").corr()["Age"].sort_values(ascending=False)
indices = data.index
# Prepare labels and correlation values, skipping the first element
(self-correlation of "Age")
labels = []
corr = []

for i in range(1, len(indices)):
labels.append(indices[i])
corr.append(data[i])
# Plot the correlations
sns.barplot(x=corr, y=labels, palette='mako')
plt.title('Correlation coefficient between different features and Age')
plt.show()

embrk=df_6['Embarked'].value_counts()
sns.set_palette('bright')
plt.figure(figsize=(10,7))
labels=embrk.index
sizes=embrk.values
plt.pie(sizes,labels=labels,autopct='%1.1f%%',shadow=True,startangle=90)
plt.show()

import matplotlib
matplotlib.rcParams.update({'font.size': 15})
plt.figure(figsize=(18,9))
cols_out = ["restecg", "chol", "slp", "age",'exng']
sns.pairplot(df_3[cols_out],hue="exng",diag_kind="hist",palette="tab10")
plt.show()

fig, ax = plt.subplots(figsize = (18,8))
sns.countplot(x= df_5["Wine"])
plt.title("Wine Quality Count",fontsize=20,color='#1a4441',font='ComicSans Ms',pad=20)
plt.xlabel("Quality ",fontsize=15,color='#1a4441',font='Comic Sans Ms')
plt.ylabel("Count",fontsize=15,color='#1a4441',font='Comic Sans Ms');
total = len(df_5)

for p in ax.patches:

percentage = f'{100 * p.get_height() / total:.1f}%\n'
x = p.get_x() + p.get_width() / 2
y = p.get_height()
ax.annotate(percentage, (x, y), ha='center', va='center')

print("Skewly distributed columns by skewness value:\n")
skew_df = df_5.skew().sort_values()
fig,ax = plt.subplots(figsize=(25,7))
ax.bar(x = skew_df[(skew_df<2)& (skew_df>-2)].index, height =skew_df[(skew_df<2)& (skew_df>-2)], color = "g", label= "Semi-normal distribition")
ax.bar(x = skew_df[skew_df>2].index, height = skew_df[skew_df>2], color= "r", label = "Positively skewed features")
ax.bar(x = skew_df[skew_df<-2].index, height = skew_df[skew_df<-2], color= "b", label = "Negatively skewed features")
ax.legend()
fig.suptitle("Skewness of numerical columns",fontsize = 20)
ax.tick_params(labelrotation=90)

import math
import matplotlib.pyplot as plt
import seaborn as sns
# Continuous features and setup
cont_features = ['Alcohol', 'Malic.acid', 'Ash', 'Acl', 'Mg', 'Phenols']
y = 3
x = math.ceil(len(cont_features) / y)
# Create subplots
plt.subplots(x, y, figsize=(25, 10))
# Define palette
palette = ['#e60000', '#FAFAD2', '#660000', '#DEB078', '#FF8C00', 'black']
# Plot each feature

for i in range(1, len(cont_features) + 1):

plt.subplot(x, y, i)
sns.boxplot(data=df_5, y=cont_features[i - 1], x='Wine', palette=palette)
# Adjust layout and show
plt.tight_layout()
plt.show()

sns.boxplot(x='day', y='total_bill', hue='sex', data=df, linewidth=2.5, palette='Dark2')

sns.boxplot(x='sex', y='total_bill', data=df, linewidth=2.5, palette='Dark2')

# Calculate statistics
mean_val = df['total_bill'].mean()
median_val = df['total_bill'].median()
q1_val = df['total_bill'].quantile(0.25)
q3_val = df['total_bill'].quantile(0.75)
# Create the boxplot
sns.boxplot(y='total_bill', data=df, linewidth=2.5, palette='Dark2')
# Add Title and Labels
plt.title('Box Plot with Mean, Median, and IQR')
plt.ylabel('Total Bill')
# Add text annotations for the actual values in the bottom-right corner
plt.text(0.8, df['total_bill'].min() + 50, f'Mean = {mean_val:.2f}', color='red', ha='left', fontsize=10)
plt.text(0.8, df['total_bill'].min() + 44, f'Median (Q2) = {median_val:.2f}', color='green', ha='left', fontsize=10)
plt.text(0.8, df['total_bill'].min() + 47, f'Q1 (25%) = {q1_val:.2f}', color='blue', ha='left', fontsize=10)
plt.text(0.8, df['total_bill'].min() + 41, f'Q3 (75%) = {q3_val:.2f}', color='blue', ha='left', fontsize=10)
# Adjust xlim and ylim to make sure text annotations fit
plt.xlim(-0.5, 1.5)
plt.ylim(0, df['total_bill'].max() + 5)
# Show plot
plt.show()

sns.pairplot(df_5[['Alcohol', 'Malic.acid', 'Ash', 'Acl', 'Mg', 'Phenols']],
kind="reg",
diag_kind='kde',
plot_kws={'line_kws':{'color':'red'}},
corner=True,
height=2) # Adjust height as needed
plt.tight_layout()
plt.show()

features = ['Alcohol','Malic.acid','Ash']
fig, axs = plt.subplots(1,3, figsize=(16,6))
for f, ax in zip(features,axs.ravel()):

sns.histplot(df_5, x=f, ax=ax)

plt.show()

plt.figure(figsize=(8,5))
ax = sns.kdeplot(data=df_2, x='age', multiple='stack', palette='tab10')
# Calculate mean, mode, and median for the 'Age' column
age_data = df_2['age'].dropna()
# Drop any missing values from 'Age'
mean_age = age_data.mean()
# Calculate mean
mode_age = age_data.mode().values[0]
# Calculate mode (use the first mode if there are multiple)
median_age = age_data.median()
# Calculate median
# Add vertical lines for mean, mode, and median
plt.axvline(mean_age, color='blue', linestyle='--', label=f'Mean: {mean_age:.1f}')
plt.axvline(mode_age, color='green', linestyle='-', label=f'Mode: {mode_age:.1f}', alpha=0.7)
plt.axvline(median_age, color='red', linestyle='-.', label=f'Median: {median_age:.1f}', alpha=0.7)
# Customize and display the plot
plt.legend()
plt.title('KDE Plot of Age with Mean, Mode, and Median')
plt.xlabel('Age')
plt.ylabel('Density')
plt.show()

sns.violinplot(x="day", y="total_bill", data=df)

sns.stripplot(x="time", y="total_bill", hue="sex", data=df)

sns.stripplot(x="day" , y="total_bill" ,
hue="sex" ,data=df ,
jitter=True ,alpha = 0.6 ,size = 11 ,edgecolor = 'purple' ,linewidth=1)

sns.scatterplot(x='total_bill',y='tip',hue='sex',data=df)

sns.jointplot(x="chol", y="thalachh",
data=df_3,kind="hist",hue='sex')

sns.boxenplot( x='time', y="total_bill", hue='sex', data=df)

sns.jointplot(x="chol", y="thalachh",
data=df_3,kind="kde",hue='sex')

g = sns.JointGrid(data=df_3, x="age", y="chol", hue="output")

g.plot(sns.scatterplot, sns.histplot)

g = sns.JointGrid(data=df_3, x="age", y="chol")
g.plot(sns.scatterplot, sns.histplot)