数据分析最有用的Top 50 Matplotlib图（带有完整的Python代码）(下)

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
sns.boxplot(x='class', y='hwy', data=df, notch=False)

# Add N Obs inside boxplot (optional)
def add_n_obs(df,group_col,y):
    medians_dict = {grp[0]:grp[1][y].median() for grp in df.groupby(group_col)}
    xticklabels = [x.get_text() for x in plt.gca().get_xticklabels()]
    n_obs = df.groupby(group_col)[y].size().values
    for (x, xticklabel), n_ob in zip(enumerate(xticklabels), n_obs):
        plt.text(x, medians_dict[xticklabel]*1.01, "#obs : "+str(n_ob), horizontalalignment='center', fontdict={'size':14}, color='white')

add_n_obs(df,group_col='class',y='hwy')    

# Decoration
plt.title('Box Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.ylim(10, 40)
plt.show()

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
sns.boxplot(x='class', y='hwy', data=df, hue='cyl')
sns.stripplot(x='class', y='hwy', data=df, color='black', size=3, jitter=1)

for i in range(len(df['class'].unique())-1):
    plt.vlines(i+.5, 10, 45, linestyles='solid', colors='gray', alpha=0.2)

# Decoration
plt.title('Box Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.legend(title='Cylinders')
plt.show()

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
sns.violinplot(x='class', y='hwy', data=df, scale='width', inner='quartile')

# Decoration
plt.title('Violin Plot of Highway Mileage by Vehicle Class', fontsize=22)
plt.show()

# Read data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/email_campaign_funnel.csv")

# Draw Plot
plt.figure(figsize=(13,10), dpi= 80)
group_col = 'Gender'
order_of_bars = df.Stage.unique()[::-1]
colors = [plt.cm.Spectral(i/float(len(df[group_col].unique())-1)) for i in range(len(df[group_col].unique()))]

for c, group in zip(colors, df[group_col].unique()):
    sns.barplot(x='Users', y='Stage', data=df.loc[df[group_col]==group, :], order=order_of_bars, color=c, label=group)

# Decorations    
plt.xlabel("$Users$")
plt.ylabel("Stage of Purchase")
plt.yticks(fontsize=12)
plt.title("Population Pyramid of the Marketing Funnel", fontsize=22)
plt.legend()
plt.show()

# Load Dataset
titanic = sns.load_dataset("titanic")

# Plot
g = sns.catplot("alive", col="deck", col_wrap=4,
                data=titanic[titanic.deck.notnull()],
                kind="count", height=3.5, aspect=.8, 
                palette='tab20')

fig.suptitle('sf')
plt.show()

# Load Dataset
titanic = sns.load_dataset("titanic")

# Plot
sns.catplot(x="age", y="embark_town",
            hue="sex", col="class",
            data=titanic[titanic.embark_town.notnull()],
            orient="h", height=5, aspect=1, palette="tab10",
            kind="violin", dodge=True, cut=0, bw=.2)

#! pip install pywaffle
# Reference: https://stackoverflow.com/questions/41400136/how-to-do-waffle-charts-in-python-square-piechart
from pywaffle import Waffle

# Import
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size().reset_index(name='counts')
n_categories = df.shape[0]
colors = [plt.cm.inferno_r(i/float(n_categories)) for i in range(n_categories)]

# Draw Plot and Decorate
fig = plt.figure(
    FigureClass=Waffle,
    plots={
        '111': {
            'values': df['counts'],
            'labels': ["{0} ({1})".format(n[0], n[1]) for n in df[['class', 'counts']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12},
            'title': {'label': '# Vehicles by Class', 'loc': 'center', 'fontsize':18}
        },
    },
    rows=7,
    colors=colors,
    figsize=(16, 9)
)

#! pip install pywaffle
from pywaffle import Waffle

# Import
# df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
# By Class Data
df_class = df_raw.groupby('class').size().reset_index(name='counts_class')
n_categories = df_class.shape[0]
colors_class = [plt.cm.Set3(i/float(n_categories)) for i in range(n_categories)]

# By Cylinders Data
df_cyl = df_raw.groupby('cyl').size().reset_index(name='counts_cyl')
n_categories = df_cyl.shape[0]
colors_cyl = [plt.cm.Spectral(i/float(n_categories)) for i in range(n_categories)]

# By Make Data
df_make = df_raw.groupby('manufacturer').size().reset_index(name='counts_make')
n_categories = df_make.shape[0]
colors_make = [plt.cm.tab20b(i/float(n_categories)) for i in range(n_categories)]


# Draw Plot and Decorate
fig = plt.figure(
    FigureClass=Waffle,
    plots={
        '311': {
            'values': df_class['counts_class'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_class[['class', 'counts_class']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'Class'},
            'title': {'label': '# Vehicles by Class', 'loc': 'center', 'fontsize':18},
            'colors': colors_class
        },
        '312': {
            'values': df_cyl['counts_cyl'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_cyl[['cyl', 'counts_cyl']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'Cyl'},
            'title': {'label': '# Vehicles by Cyl', 'loc': 'center', 'fontsize':18},
            'colors': colors_cyl
        },
        '313': {
            'values': df_make['counts_make'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_make[['manufacturer', 'counts_make']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'Manufacturer'},
            'title': {'label': '# Vehicles by Make', 'loc': 'center', 'fontsize':18},
            'colors': colors_make
        }
    },
    rows=9,
    figsize=(16, 14)
)

# Import
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size()

# Make the plot with pandas
df.plot(kind='pie', subplots=True, figsize=(8, 8), dpi= 80)
plt.title("Pie Chart of Vehicle Class - Bad")
plt.ylabel("")
plt.show()

# Import
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size().reset_index(name='counts')

# Draw Plot
fig, ax = plt.subplots(figsize=(12, 7), subplot_kw=dict(aspect="equal"), dpi= 80)

data = df['counts']
categories = df['class']
explode = [0,0,0,0,0,0.1,0]

def func(pct, allvals):
    absolute = int(pct/100.*np.sum(allvals))
    return "{:.1f}% ({:d} )".format(pct, absolute)

wedges, texts, autotexts = ax.pie(data, 
                                  autopct=lambda pct: func(pct, data),
                                  textprops=dict(color="w"), 
                                  colors=plt.cm.Dark2.colors,
                                 startangle=140,
                                 explode=explode)

# Decoration
ax.legend(wedges, categories, title="Vehicle Class", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
plt.setp(autotexts, size=10, weight=700)
ax.set_title("Class of Vehicles: Pie Chart")
plt.show()

# pip install squarify
import squarify 

# Import Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('class').size().reset_index(name='counts')
labels = df.apply(lambda x: str(x[0]) + "
 (" + str(x[1]) + ")", axis=1)
sizes = df['counts'].values.tolist()
colors = [plt.cm.Spectral(i/float(len(labels))) for i in range(len(labels))]

# Draw Plot
plt.figure(figsize=(12,8), dpi= 80)
squarify.plot(sizes=sizes, label=labels, color=colors, alpha=.8)

# Decorate
plt.title('Treemap of Vechile Class')
plt.axis('off')
plt.show()

import random

# Import Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")

# Prepare Data
df = df_raw.groupby('manufacturer').size().reset_index(name='counts')
n = df['manufacturer'].unique().__len__()+1
all_colors = list(plt.cm.colors.cnames.keys())
random.seed(100)
c = random.choices(all_colors, k=n)

# Plot Bars
plt.figure(figsize=(16,10), dpi= 80)
plt.bar(df['manufacturer'], df['counts'], color=c, width=.5)
for i, val in enumerate(df['counts'].values):
    plt.text(i, val, float(val), horizontalalignment='center', verticalalignment='bottom', fontdict={'fontweight':500, 'size':12})

# Decoration
plt.gca().set_xticklabels(df['manufacturer'], rotation=60, horizontalalignment= 'right')
plt.title("Number of Vehicles by Manaufacturers", fontsize=22)
plt.ylabel('# Vehicles')
plt.ylim(0, 45)
plt.show()

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')

# Draw Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.plot('date', 'traffic', data=df, color='tab:red')

# Decoration
plt.ylim(50, 750)
xtick_location = df.index.tolist()[::12]
xtick_labels = [x[-4:] for x in df.date.tolist()[::12]]
plt.xticks(ticks=xtick_location, labels=xtick_labels, rotation=0, fontsize=12, horizontalalignment='center', alpha=.7)
plt.yticks(fontsize=12, alpha=.7)
plt.title("Air Passengers Traffic (1949 - 1969)", fontsize=22)
plt.grid(axis='both', alpha=.3)

# Remove borders
plt.gca().spines["top"].set_alpha(0.0)    
plt.gca().spines["bottom"].set_alpha(0.3)
plt.gca().spines["right"].set_alpha(0.0)    
plt.gca().spines["left"].set_alpha(0.3)   
plt.show()

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')

# Get the Peaks and Troughs
data = df['traffic'].values
doublediff = np.diff(np.sign(np.diff(data)))
peak_locations = np.where(doublediff == -2)[0] + 1

doublediff2 = np.diff(np.sign(np.diff(-1*data)))
trough_locations = np.where(doublediff2 == -2)[0] + 1

# Draw Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.plot('date', 'traffic', data=df, color='tab:blue', label='Air Traffic')
plt.scatter(df.date[peak_locations], df.traffic[peak_locations], marker=mpl.markers.CARETUPBASE, color='tab:green', s=100, label='Peaks')
plt.scatter(df.date[trough_locations], df.traffic[trough_locations], marker=mpl.markers.CARETDOWNBASE, color='tab:red', s=100, label='Troughs')

# Annotate
for t, p in zip(trough_locations[1::5], peak_locations[::3]):
    plt.text(df.date[p], df.traffic[p]+15, df.date[p], horizontalalignment='center', color='darkgreen')
    plt.text(df.date[t], df.traffic[t]-35, df.date[t], horizontalalignment='center', color='darkred')

# Decoration
plt.ylim(50,750)
xtick_location = df.index.tolist()[::6]
xtick_labels = df.date.tolist()[::6]
plt.xticks(ticks=xtick_location, labels=xtick_labels, rotation=90, fontsize=12, alpha=.7)
plt.title("Peak and Troughs of Air Passengers Traffic (1949 - 1969)", fontsize=22)
plt.yticks(fontsize=12, alpha=.7)

# Lighten borders
plt.gca().spines["top"].set_alpha(.0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(.0)
plt.gca().spines["left"].set_alpha(.3)

plt.legend(loc='upper left')
plt.grid(axis='y', alpha=.3)
plt.show()

from statsmodels.graphics.tsaplots import plot_acf, plot_pacf

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')

# Draw Plot
fig, (ax1, ax2) = plt.subplots(1, 2,figsize=(16,6), dpi= 80)
plot_acf(df.traffic.tolist(), ax=ax1, lags=50)
plot_pacf(df.traffic.tolist(), ax=ax2, lags=20)

# Decorate
# lighten the borders
ax1.spines["top"].set_alpha(.3); ax2.spines["top"].set_alpha(.3)
ax1.spines["bottom"].set_alpha(.3); ax2.spines["bottom"].set_alpha(.3)
ax1.spines["right"].set_alpha(.3); ax2.spines["right"].set_alpha(.3)
ax1.spines["left"].set_alpha(.3); ax2.spines["left"].set_alpha(.3)

# font size of tick labels
ax1.tick_params(axis='both', labelsize=12)
ax2.tick_params(axis='both', labelsize=12)
plt.show()

import statsmodels.tsa.stattools as stattools

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/mortality.csv')
x = df['mdeaths']
y = df['fdeaths']

# Compute Cross Correlations
ccs = stattools.ccf(x, y)[:100]
nlags = len(ccs)

# Compute the Significance level
# ref: https://stats.stackexchange.com/questions/3115/cross-correlation-significance-in-r/3128#3128
conf_level = 2 / np.sqrt(nlags)

# Draw Plot
plt.figure(figsize=(12,7), dpi= 80)

plt.hlines(0, xmin=0, xmax=100, color='gray')  # 0 axis
plt.hlines(conf_level, xmin=0, xmax=100, color='gray')
plt.hlines(-conf_level, xmin=0, xmax=100, color='gray')

plt.bar(x=np.arange(len(ccs)), height=ccs, width=.3)

# Decoration
plt.title('$Cross; Correlation; Plot:; mdeaths; vs; fdeaths$', fontsize=22)
plt.xlim(0,len(ccs))
plt.show()

from statsmodels.tsa.seasonal import seasonal_decompose
from dateutil.parser import parse

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')
dates = pd.DatetimeIndex([parse(d).strftime('%Y-%m-01') for d in df['date']])
df.set_index(dates, inplace=True)

# Decompose 
result = seasonal_decompose(df['traffic'], model='multiplicative')

# Plot
plt.rcParams.update({'figure.figsize': (10,10)})
result.plot().suptitle('Time Series Decomposition of Air Passengers')
plt.show()

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/mortality.csv')

# Define the upper limit, lower limit, interval of Y axis and colors
y_LL = 100
y_UL = int(df.iloc[:, 1:].max().max()*1.1)
y_interval = 400
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange']    

# Draw Plot and Annotate
fig, ax = plt.subplots(1,1,figsize=(16, 9), dpi= 80)    

columns = df.columns[1:]  
for i, column in enumerate(columns):    
    plt.plot(df.date.values, df[column].values, lw=1.5, color=mycolors[i])    
    plt.text(df.shape[0]+1, df[column].values[-1], column, fontsize=14, color=mycolors[i])

# Draw Tick lines  
for y in range(y_LL, y_UL, y_interval):    
    plt.hlines(y, xmin=0, xmax=71, colors='black', alpha=0.3, linestyles="--", lw=0.5)

# Decorations    
plt.tick_params(axis="both", which="both", bottom=False, top=False,    
                labelbottom=True, left=False, right=False, labelleft=True)        

# Lighten borders
plt.gca().spines["top"].set_alpha(.3)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(.3)
plt.gca().spines["left"].set_alpha(.3)

plt.title('Number of Deaths from Lung Diseases in the UK (1974-1979)', fontsize=22)
plt.yticks(range(y_LL, y_UL, y_interval), [str(y) for y in range(y_LL, y_UL, y_interval)], fontsize=12)    
plt.xticks(range(0, df.shape[0], 12), df.date.values[::12], horizontalalignment='left', fontsize=12)    
plt.ylim(y_LL, y_UL)    
plt.xlim(-2, 80)    
plt.show()

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv")

x = df['date']
y1 = df['psavert']
y2 = df['unemploy']

# Plot Line1 (Left Y Axis)
fig, ax1 = plt.subplots(1,1,figsize=(16,9), dpi= 80)
ax1.plot(x, y1, color='tab:red')

# Plot Line2 (Right Y Axis)
ax2 = ax1.twinx()  # instantiate a second axes that shares the same x-axis
ax2.plot(x, y2, color='tab:blue')

# Decorations
# ax1 (left Y axis)
ax1.set_xlabel('Year', fontsize=20)
ax1.tick_params(axis='x', rotation=0, labelsize=12)
ax1.set_ylabel('Personal Savings Rate', color='tab:red', fontsize=20)
ax1.tick_params(axis='y', rotation=0, labelcolor='tab:red' )
ax1.grid(alpha=.4)

# ax2 (right Y axis)
ax2.set_ylabel("# Unemployed (1000's)", color='tab:blue', fontsize=20)
ax2.tick_params(axis='y', labelcolor='tab:blue')
ax2.set_xticks(np.arange(0, len(x), 60))
ax2.set_xticklabels(x[::60], rotation=90, fontdict={'fontsize':10})
ax2.set_title("Personal Savings Rate vs Unemployed: Plotting in Secondary Y Axis", fontsize=22)
fig.tight_layout()
plt.show()

from scipy.stats import sem

# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/user_orders_hourofday.csv")
df_mean = df.groupby('order_hour_of_day').quantity.mean()
df_se = df.groupby('order_hour_of_day').quantity.apply(sem).mul(1.96)

# Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.ylabel("# Orders", fontsize=16)  
x = df_mean.index
plt.plot(x, df_mean, color="white", lw=2) 
plt.fill_between(x, df_mean - df_se, df_mean + df_se, color="#3F5D7D")  

# Decorations
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(1)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(1)
plt.xticks(x[::2], [str(d) for d in x[::2]] , fontsize=12)
plt.title("User Orders by Hour of Day (95% confidence)", fontsize=22)
plt.xlabel("Hour of Day")

s, e = plt.gca().get_xlim()
plt.xlim(s, e)

# Draw Horizontal Tick lines  
for y in range(8, 20, 2):    
    plt.hlines(y, xmin=s, xmax=e, colors='black', alpha=0.5, linestyles="--", lw=0.5)

plt.show()

"Data Source: https://www.kaggle.com/olistbr/brazilian-ecommerce#olist_orders_dataset.csv"
from dateutil.parser import parse
from scipy.stats import sem

# Import Data
df_raw = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/orders_45d.csv', 
                     parse_dates=['purchase_time', 'purchase_date'])

# Prepare Data: Daily Mean and SE Bands
df_mean = df_raw.groupby('purchase_date').quantity.mean()
df_se = df_raw.groupby('purchase_date').quantity.apply(sem).mul(1.96)

# Plot
plt.figure(figsize=(16,10), dpi= 80)
plt.ylabel("# Daily Orders", fontsize=16)  
x = [d.date().strftime('%Y-%m-%d') for d in df_mean.index]
plt.plot(x, df_mean, color="white", lw=2) 
plt.fill_between(x, df_mean - df_se, df_mean + df_se, color="#3F5D7D")  

# Decorations
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(1)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(1)
plt.xticks(x[::6], [str(d) for d in x[::6]] , fontsize=12)
plt.title("Daily Order Quantity of Brazilian Retail with Error Bands (95% confidence)", fontsize=20)

# Axis limits
s, e = plt.gca().get_xlim()
plt.xlim(s, e-2)
plt.ylim(4, 10)

# Draw Horizontal Tick lines  
for y in range(5, 10, 1):    
    plt.hlines(y, xmin=s, xmax=e, colors='black', alpha=0.5, linestyles="--", lw=0.5)

plt.show()

# Import Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/nightvisitors.csv')

# Decide Colors 
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange', 'tab:brown', 'tab:grey', 'tab:pink', 'tab:olive']      

# Draw Plot and Annotate
fig, ax = plt.subplots(1,1,figsize=(16, 9), dpi= 80)
columns = df.columns[1:]
labs = columns.values.tolist()

# Prepare data
x  = df['yearmon'].values.tolist()
y0 = df[columns[0]].values.tolist()
y1 = df[columns[1]].values.tolist()
y2 = df[columns[2]].values.tolist()
y3 = df[columns[3]].values.tolist()
y4 = df[columns[4]].values.tolist()
y5 = df[columns[5]].values.tolist()
y6 = df[columns[6]].values.tolist()
y7 = df[columns[7]].values.tolist()
y = np.vstack([y0, y2, y4, y6, y7, y5, y1, y3])

# Plot for each column
labs = columns.values.tolist()
ax = plt.gca()
ax.stackplot(x, y, labels=labs, colors=mycolors, alpha=0.8)

# Decorations
ax.set_title('Night Visitors in Australian Regions', fontsize=18)
ax.set(ylim=[0, 100000])
ax.legend(fontsize=10, ncol=4)
plt.xticks(x[::5], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(10000, 100000, 20000), fontsize=10)
plt.xlim(x[0], x[-1])

# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)

plt.show()

# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv")

# Prepare Data
x = df['date'].values.tolist()
y1 = df['psavert'].values.tolist()
y2 = df['uempmed'].values.tolist()
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange', 'tab:brown', 'tab:grey', 'tab:pink', 'tab:olive']      
columns = ['psavert', 'uempmed']

# Draw Plot 
fig, ax = plt.subplots(1, 1, figsize=(16,9), dpi= 80)
ax.fill_between(x, y1=y1, y2=0, label=columns[1], alpha=0.5, color=mycolors[1], linewidth=2)
ax.fill_between(x, y1=y2, y2=0, label=columns[0], alpha=0.5, color=mycolors[0], linewidth=2)

# Decorations
ax.set_title('Personal Savings Rate vs Median Duration of Unemployment', fontsize=18)
ax.set(ylim=[0, 30])
ax.legend(loc='best', fontsize=12)
plt.xticks(x[::50], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(2.5, 30.0, 2.5), fontsize=10)
plt.xlim(-10, x[-1])

# Draw Tick lines  
for y in np.arange(2.5, 30.0, 2.5):    
    plt.hlines(y, xmin=0, xmax=len(x), colors='black', alpha=0.3, linestyles="--", lw=0.5)

# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)
plt.show()

import matplotlib as mpl
import calmap

# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/yahoo.csv", parse_dates=['date'])
df.set_index('date', inplace=True)

# Plot
plt.figure(figsize=(16,10), dpi= 80)
calmap.calendarplot(df['2014']['VIX.Close'], fig_kws={'figsize': (16,10)}, yearlabel_kws={'color':'black', 'fontsize':14}, subplot_kws={'title':'Yahoo Stock Prices'})
plt.show()

from dateutil.parser import parse 

# Import Data
df = pd.read_csv('https://github.com/selva86/datasets/raw/master/AirPassengers.csv')

# Prepare data
df['year'] = [parse(d).year for d in df.date]
df['month'] = [parse(d).strftime('%b') for d in df.date]
years = df['year'].unique()

# Draw Plot
mycolors = ['tab:red', 'tab:blue', 'tab:green', 'tab:orange', 'tab:brown', 'tab:grey', 'tab:pink', 'tab:olive', 'deeppink', 'steelblue', 'firebrick', 'mediumseagreen']      
plt.figure(figsize=(16,10), dpi= 80)

for i, y in enumerate(years):
    plt.plot('month', 'traffic', data=df.loc[df.year==y, :], color=mycolors[i], label=y)
    plt.text(df.loc[df.year==y, :].shape[0]-.9, df.loc[df.year==y, 'traffic'][-1:].values[0], y, fontsize=12, color=mycolors[i])

# Decoration
plt.ylim(50,750)
plt.xlim(-0.3, 11)
plt.ylabel('$Air Traffic$')
plt.yticks(fontsize=12, alpha=.7)
plt.title("Monthly Seasonal Plot: Air Passengers Traffic (1949 - 1969)", fontsize=22)
plt.grid(axis='y', alpha=.3)

# Remove borders
plt.gca().spines["top"].set_alpha(0.0)    
plt.gca().spines["bottom"].set_alpha(0.5)
plt.gca().spines["right"].set_alpha(0.0)    
plt.gca().spines["left"].set_alpha(0.5)   
# plt.legend(loc='upper right', ncol=2, fontsize=12)
plt.show()

import scipy.cluster.hierarchy as shc

# Import Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/USArrests.csv')

# Plot
plt.figure(figsize=(16, 10), dpi= 80)  
plt.title("USArrests Dendograms", fontsize=22)  
dend = shc.dendrogram(shc.linkage(df[['Murder', 'Assault', 'UrbanPop', 'Rape']], method='ward'), labels=df.State.values, color_threshold=100)  
plt.xticks(fontsize=12)
plt.show()

from sklearn.cluster import AgglomerativeClustering
from scipy.spatial import ConvexHull

# Import Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/USArrests.csv')

# Agglomerative Clustering
cluster = AgglomerativeClustering(n_clusters=5, affinity='euclidean', linkage='ward')  
cluster.fit_predict(df[['Murder', 'Assault', 'UrbanPop', 'Rape']])  

# Plot
plt.figure(figsize=(14, 10), dpi= 80)  
plt.scatter(df.iloc[:,0], df.iloc[:,1], c=cluster.labels_, cmap='tab10')  

# Encircle
def encircle(x,y, ax=None, **kw):
    if not ax: ax=plt.gca()
    p = np.c_[x,y]
    hull = ConvexHull(p)
    poly = plt.Polygon(p[hull.vertices,:], **kw)
    ax.add_patch(poly)

# Draw polygon surrounding vertices    
encircle(df.loc[cluster.labels_ == 0, 'Murder'], df.loc[cluster.labels_ == 0, 'Assault'], ec="k", fc="gold", alpha=0.2, linewidth=0)
encircle(df.loc[cluster.labels_ == 1, 'Murder'], df.loc[cluster.labels_ == 1, 'Assault'], ec="k", fc="tab:blue", alpha=0.2, linewidth=0)
encircle(df.loc[cluster.labels_ == 2, 'Murder'], df.loc[cluster.labels_ == 2, 'Assault'], ec="k", fc="tab:red", alpha=0.2, linewidth=0)
encircle(df.loc[cluster.labels_ == 3, 'Murder'], df.loc[cluster.labels_ == 3, 'Assault'], ec="k", fc="tab:green", alpha=0.2, linewidth=0)
encircle(df.loc[cluster.labels_ == 4, 'Murder'], df.loc[cluster.labels_ == 4, 'Assault'], ec="k", fc="tab:orange", alpha=0.2, linewidth=0)

# Decorations
plt.xlabel('Murder'); plt.xticks(fontsize=12)
plt.ylabel('Assault'); plt.yticks(fontsize=12)
plt.title('Agglomerative Clustering of USArrests (5 Groups)', fontsize=22)
plt.show()

from pandas.plotting import andrews_curves

# Import
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv")
df.drop(['cars', 'carname'], axis=1, inplace=True)

# Plot
plt.figure(figsize=(12,9), dpi= 80)
andrews_curves(df, 'cyl', colormap='Set1')

# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)

plt.title('Andrews Curves of mtcars', fontsize=22)
plt.xlim(-3,3)
plt.grid(alpha=0.3)
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
plt.show()

from pandas.plotting import parallel_coordinates

# Import Data
df_final = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/diamonds_filter.csv")

# Plot
plt.figure(figsize=(12,9), dpi= 80)
parallel_coordinates(df_final, 'cut', colormap='Dark2')

# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)

plt.title('Parallel Coordinated of Diamonds', fontsize=22)
plt.grid(alpha=0.3)
plt.xticks(fontsize=12)
plt.yticks(fontsize=12)
plt.show()