
import pandas as pd 
import matplotlib.pyplot as plt
import seaborn as sns 
import numpy as np


large = 22; med = 16; small = 12
params = {'axes.titlesize': large,
          'legend.fontsize': med,
          'figure.figsize': (14, 5),
          'axes.labelsize': med,
          'axes.titlesize': med,
          'xtick.labelsize': med,
          'ytick.labelsize': med,
          'figure.titlesize': large}

plt.rcParams.update(params)


x1,x2 = [i for i in range(1,20,2)], [i for i in range(55,40,-1)]
y1,y2 = [i for i in range(1,20,2)], [i for i in range(55,40,-1)]

fig, axes = plt.subplots(1,3)

sns.lineplot( x=x1, y=y1,ax = axes[0]) # if axes has more than 1 dim then two values!
sns.lineplot( x=x2, y=y2,ax = axes[1]) 

g1 = sns.lineplot( x=x1, y=y1, ax = axes[2], label="multy_1",  linestyle='dashed', marker = 's') 
g2 = sns.lineplot( x=x2, y=y2, ax = axes[2], label="multy_2", linestyle='dashdot') 
axes[2].axvline(x=30, color='black', linestyle='dotted') # added vertical line at x = 30.

axes[0].set_title("First")
axes[1].set_title("Second")
axes[2].set_title("Third")

axes[0].set_xlabel("yep")
axes[1].set_xlabel("yep")
axes[2].set_xlabel("yep")

axes[2].legend(loc="lower center")
axes[2].set_ylim(-50,70)  # if using not axes just use ylim() without set_*
axes[2].set_xlim(-5,70)  

# styles! --> plt.style.available
plt.style.use("bmh")

plt.show()


plt.figure(figsize=(10,7), dpi=80)
x = np.linspace(-3, 3*np.pi, 1000)

sine = sns.lineplot(x=x, y=np.sin(x), label='sine')
cosine = sns.lineplot(x=x, y=np.cos(x), label='cosine')  # avoid warning put explict x = ..., y = ...

plt.axhline(y=0.0, color='black', linestyle='dotted', label='H')  # axes horizontal line
plt.axvline(x=0.0, color='black', linestyle='dotted', label='V')  # axes vertical line

plt.title("Sine-Cosine", )  
plt.xlabel("Time")
plt.ylabel("Value")
plt.xlim(-5,10)
plt.ylim(-2,2)

#legend
plt.legend(frameon=True,                                   # legend border
           framealpha=1,                                   # transparency of border
           ncol=2,                                         # num columns
           shadow=True,                                    # shadow on
           borderpad=0.5,                                    # thickness of border
           title='Sines and Cosines')  

# Text annotation

plt.annotate('Peaks', xy=(1.6, 1.0), xytext=(1.6, 1.3),
             bbox=dict(boxstyle='square', fc='green', linewidth=0.1),
             arrowprops=dict(facecolor='green', shrink=0.01, width=0.1), 
             fontsize=12, color='white', horizontalalignment='center')

plt.text(x=2.5, y=-1.3,  s= "2.5\ndegrees", horizontalalignment='center', color='red') # transform=plt.gca().transData,

plt.show()


## Customize subplot layout


fig = plt.figure()
ax1 = plt.subplot2grid((3,3), (0,0), colspan=2, rowspan=2) # topleft
ax3 = plt.subplot2grid((3,3), (0,2), rowspan=3)            # right
ax4 = plt.subplot2grid((3,3), (2,0))                       # bottom left
ax5 = plt.subplot2grid((3,3), (2,1))                       # bottom right

sns.lineplot(ax= ax5, x=[1,2,3], y=[0,1,0]) # MUST USE AX=
ax1.plot([1,2,3],[2,3,2])
ax4.plot([1,2,3], [0,1,0])
ax3.plot([1,2,3], [0,1,2])

fig.tight_layout() # automatically fix the subplots!

plt.show()


fig, axes = plt.subplots()
axes.plot([1,3,4],[0,0,0], label='main', color='firebrick', linestyle='dashed')
axes.set_xlim(-5,5)
axes.set_ylim(-5,5) # lim of subplot! set_ylim!
axes.legend(loc='best')

inner = fig.add_axes([0.2,0.3,0.2,0.3])
inner.plot([3,2,1],[4,2,1], label='inner', color="royalblue", linestyle='dotted')
inner.legend(loc='best')

plt.show()


midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")

fig = plt.figure(figsize=(14, 7), dpi= 200)

plt.scatter(x='area', y='poptotal', data=midwest, #date
            s = 'dot_size',  # s = shape (n, ), optional as The marker size in points**2  
            c = 'popdensity',  # c = color! in this case is according to popdensity variable in the df!
            cmap='icefire', # cmap = colormap aka palette
            edgecolors='black',
            linewidths=1)

plt.colorbar() # bar on the right!

plt.title("Bubble Plot of PopTotal vs Area\n(color: 'popdensity' & size: 'dot_size' - both are numeric columns in midwest)", fontsize=16)
plt.show()


plt.figure(figsize=(10,10))
sns.scatterplot(data=midwest, x='area', y='poptotal',
               hue = 'category', # very important! 
               size='dot_size',
               cmap="Reds")
    
plt.title("Hue category in SNS")
plt.show()


## KDE, Kernel density distribution


iris = sns.load_dataset("iris")
setosa = iris.loc[iris["species"]=="setosa"]
virginica = iris.loc[iris["species"]=="virginica"]

sns.kdeplot(x="sepal_width",y= "sepal_length", data=setosa, 
            cmap="husl", 
            n_levels=20, # number of circles
            label='Setosa')

sns.kdeplot(x="sepal_width",y= "sepal_length", data=virginica, cmap="inferno", n_levels=20, label='Virginica')

plt.legend()
plt.title("Multiple KDE")

plt.show()


fig, axes = plt.subplots(1,2)

# must pass just one variable as x or y.
sns.histplot(ax=axes[0], data=midwest, x='popwhite',
            kde=True, # kernel distribution line
            alpha=0.3, # color related
            color="firebrick")\
            .set_title('First') # title subplot of seaborn!


sns.histplot(ax=axes[1], data=midwest, x='popblack',
            hue='state', kde=True, alpha=.3).set_title('Second')

plt.show()


fig,axes = plt.subplots(1,2)

sns.countplot(ax=axes[0], data=midwest, x ="state",
              palette= "RdYlGn").set_title('Count plot')

sns.barplot(ax = axes[1], 
            data=midwest, y= "popwhite",  x="state" ,
            palette="spring",
            capsize=0.2).set_title("Bar plot")

plt.show()


def show_values_on_bars(axs, h_v="v", space_x=0.12,space_y=0.1, fontdict=None):
    def _show_on_single_plot(ax):
        if h_v == "v":
            for p in ax.patches:
                _x = p.get_x() + p.get_width() / 2 + space_x
                _y = p.get_y() + p.get_height() + (space_y)
                if not np.isnan(p.get_width()):
                    value = round(p.get_height(),2)
                    if fontdict: ax.text(_x, _y, value, ha="left", fontdict=fontdict)
                    else: ax.text(_x, _y, value, ha="left")
        elif h_v == "h":
            for p in ax.patches:
                try:
                    _x = p.get_x() + p.get_width() + space_x
                    _y = p.get_y() + p.get_height() + space_y
                    if not np.isnan(p.get_width()):
                        value = round(p.get_width(),2)
                        if value < 0: _x-=0.27
                        if fontdict: ax.text(_x, _y, value, ha="left", fontdict=fontdict)
                        else: ax.text(_x, _y, value, ha="left")
                except: print(f'Error while preparing {str(p)}')
    if isinstance(axs, np.ndarray):
        for idx, ax in np.ndenumerate(axs):
            _show_on_single_plot(ax)
    else:
        _show_on_single_plot(axs)


df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.reset_index(inplace=True, drop=False)
df.sort_values(by='cty', inplace=True)
fig = plt.figure(figsize=(15,5))

g1 = sns.barplot(data=df, x='manufacturer', y='cty', 
            color='firebrick')

g1.set_ylim(0,30)
show_values_on_bars(g1, 'v', fontdict=dict(size=15), space_x=-0.4, space_y=1)

for item in g1.get_xticklabels(): # tick rotation 
    item.set_rotation(45)

import matplotlib.patches as patches  # colored boxes on xticks
p1 = patches.Rectangle((.57, -0.005), width=.33, height=.13, alpha=.1, facecolor='green', 
                   transform=fig.transFigure)
p2 = patches.Rectangle((.124, -0.005), width=.446, height=.13, alpha=.1, facecolor='red', 
                   transform=fig.transFigure)
fig.add_artist(p1)
fig.add_artist(p2)
plt.show()


sns.lineplot(data=midwest[(midwest.state == 'IL') | (midwest.state == 'IN')],
            x = "area",
            y="popdensity",
            hue ="state",
            palette="dark",
            ci = 0.8).set_title("Line Plot")

plt.show()


fig, axes = plt.subplots(4,1, figsize=(15,20))

# BOXPLOT
sns.boxplot(ax = axes[0], data=midwest, y = "state", x ="percadultpoverty", 
            #hue="sex",    # hue according to some category if usefull
            palette="husl",
            orient = "h")  # h or v. must change also the x,y data.

m = 0
for i in (midwest.state.unique()):
    filtered = midwest.percadultpoverty[midwest.state == i]
    axes[0].text(y = m, x = filtered.median(), 
                s= str(len(filtered)), 
                fontdict=dict(size=15, color='white'),
                rotation=270)
    m+=1
    
#VIOLINPLOT
sns.violinplot(ax = axes[1], data=midwest, y = "state", x ="percadultpoverty", 
            palette="Spectral",
            orient = "h", 
            inner='quartile')  # {“box”, “quartile”, “point”, “stick”} 

#BOX+STRIP
sns.boxplot(ax = axes[2], data=midwest, y = "state", x ="percadultpoverty", 
            palette="magma",
            orient = "h")  
sns.stripplot(ax = axes[2], data=midwest, y = "state", x ="percadultpoverty", 
            palette="magma",
            orient = "h",
            jitter= 0.5)

#BOX + SWARM
sns.boxplot(ax = axes[3], data=midwest, y = "state", x ="percadultpoverty", 
            palette="Reds",
            orient = "h")  

sns.swarmplot(ax = axes[3], data=midwest, y = "state", x ="percadultpoverty", 
            palette="Reds",
            orient = "h")


plt.show()


sns.lmplot(data=midwest[(midwest.state == 'IL') | (midwest.state == 'MI')], 
           x='popdensity', y='popblack', 
           col='state',  # if in one plot put hue instead
           height=4, aspect=1.6, palette='tab10', 
           scatter_kws=dict(s=60, linewidths=.7, edgecolors='black'),
           legend=False)

plt.show()


sns.set_style("dark")
sns.stripplot(x="category", y="popdensity", data=midwest,
              palette="Reds", 
              dodge=True, # used to better represent the HUE!
              hue="state",
              linewidth= 1,
              marker="d",
              size = 10,
              alpha=0.6)
plt.show()


midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv")

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

marginal = sns.JointGrid(data=midwest, x = "popwhite",   y="popdensity", hue='state')
marginal.plot_joint(sns.scatterplot, color="slateblue")
marginal.plot_marginals(sns.boxplot, color="mediumseagreen")
marginal.plot_marginals(sns.swarmplot, color="orange", s=2)
marginal.plot_marginals(sns.rugplot, color="coral", height=-.15)

plt.show()

<Figure size 720x720 with 0 Axes>


iris = sns.load_dataset("iris")
fig = plt.figure(figsize=(10,10))

grid = sns.PairGrid(data=iris, hue="species", 
                    palette="dark", 
                    hue_kws={"marker":["d","s","+"]})

grid.map_diag(sns.histplot)
grid.map_upper(sns.scatterplot)
grid.map_lower(sns.kdeplot)
#grid.add_legend()

plt.show()

<Figure size 720x720 with 0 Axes>


titanic = sns.load_dataset("titanic")
titanic = titanic[ ~ pd.isna(titanic.deck) ]
sns.catplot( x= 'alive', data= titanic, col= 'deck',
           kind = 'count' , col_wrap=4)

plt.show()

Data Viz Basic

Subplots¶

Multiple Lines, V,H and Text annotation¶

Inner Plot¶

Basics Plot¶

ScatterPlot¶

Seaborn HUE options¶

Histogram and Displot¶

Barplot¶

Bar Chart, tick rotation¶

LinePlot¶

Box, Box + Stripp & jitter, Box + Swarm, Violin Plot, Text inside boxplot¶

LMPLOT, scatter with best fit line¶

Stripplot with Jitter¶

Marginal Plots¶

Pairwise Plot¶

Categorical Plot¶