3.Matplot

• import seaborn as sns 데이터 시각화
• %matplotlib inline 매직키워드, 새창 안띄우고 셀 바로 아래에 생성
• scatter plot : 산점도 그리기

categories = np.unique(midwest['category'])
colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))]

plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')

for i, category in enumerate(categories):
#i,category는 enumerate로 형성된 tuple을 unpacking 해준 것
    plt.scatter('area', 'poptotal',
                data=midwest.loc[midwest.category==category, :],
                s=20, c=[colors[i]], label=str(category))
    # scatter그리기

plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000),
              xlabel='Area', ylabel='Population')
# 축 설정

plt.xticks(fontsize=12); plt.yticks(fontsize=12)
plt.title("Test", fontsize=22)
plt.legend(fontsize=12)    # heu 글씨 크기 설정
plt.show()

-

• scatter plot convex hull로 강조

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)

midwest_encircle_data = midwest.loc[midwest.state=='IN', :] # 인도사람들의 분포는?

encircle(midwest_encircle_data.area, midwest_encircle_data.poptotal, ec="k", fc="gold", alpha=0.1)
encircle(midwest_encircle_data.area, midwest_encircle_data.poptotal, ec="firebrick", fc="none", linewidth=1.5)

-

• grid로 구역 나눠서 sub plot 추가

ax_main = fig.add_subplot(grid[:-1, :-1]) ->메인 플롯
ax_right = fig.add_subplot(grid[:-1, -1], xticklabels=[], yticklabels=[]) ->오른쪽
ax_bottom = fig.add_subplot(grid[-1, :-1], xticklabels=[], yticklabels=[]) ->하단

-

• heatmap 사용

plt.figure(figsize=(12,10), dpi= 80)

sns.heatmap(df.corr(), xticklabels=df.corr().columns, yticklabels=df.corr().columns, cmap='RdYlGn', center=0, annot=True)

• 
• hline: horizontal line

plt.figure(figsize=(14,10), dpi= 80)
plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z, color=df.colors, alpha=0.4, linewidth=5)

• 
• kdeplot: 밀도플롯

plt.figure(figsize=(16,10), dpi= 80)
sns.kdeplot(df.loc[df['cyl'] == 4, "cty"], shade=True, color="g", label="Cyl=4", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 5, "cty"], shade=True, color="deeppink", label="Cyl=5", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 6, "cty"], shade=True, color="dodgerblue", label="Cyl=6", alpha=.7)
sns.kdeplot(df.loc[df['cyl'] == 8, "cty"], shade=True, color="orange", label="Cyl=8", alpha=.7)

• 
• distplot: 분포플롯

plt.figure(figsize=(13,10), dpi= 80)
sns.distplot(df.loc[df['class'] == 'compact', "cty"], color="dodgerblue", label="Compact", hist_kws={'alpha':.7}, kde_kws={'linewidth':3})
sns.distplot(df.loc[df['class'] == 'suv', "cty"], color="orange", label="SUV", hist_kws={'alpha':.7}, kde_kws={'linewidth':3})
sns.distplot(df.loc[df['class'] == 'minivan', "cty"], color="g", label="minivan", hist_kws={'alpha':.7}, kde_kws={'linewidth':3})
plt.ylim(0, 0.35)

• 
• piechart

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)

• 
• bar chart

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})

-

• . dendogram: hierarchy 구조

plt.figure(figsize=(16, 10), dpi= 80)
plt.title("Test11", 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()

-