[Python] 資料視覺化的sample code集

這裡記錄常用的資料視覺化會使用到的python code，方便查詢使用。(隨時增加~)

Python常用的資料視覺化library：
    1. matplotlib

import matplotlib.pyplot as plt

---

折線圖： plt.plot()

plt.plot([-1,2,3.1,4], [1,2,3,4], [1,2,3,4], [2,3,0,1])  ## (x-vals, y-vals, ...)
plt.axis([-2, 5, 0, 5])  ## axis: [xmin, xmax, ymin, ymax]
plt.ylabel("value")
plt.show()

---

柱狀圖：plt.bar()

names = ['Tom', 'Mary', 'Tim', 'Ken']
math_scores = [80, 85, 66, 90]
eng_scores = [60, 75, 60, 80]
xAxis = np.arange(len(names))+1
plt.bar(xAxis, math_scores, color='lightskyblue', width=0.2, label='math')
plt.bar(xAxis+0.3, eng_scores, color='yellowgreen', width=0.2, label='english')
plt.title('1st Exam', fontsize=14)
plt.xlabel('Students', fontsize=14)
plt.ylabel('Score', fontsize=14)
plt.xticks(xAxis, names)
plt.legend(loc="upper center")
plt.show()

---

散佈圖：plt.scatter()

speed = [4, 4, 7, 7, 8]
dist = [2, 10, 4, 22, 16]

plt.scatter(speed, dist)
plt.grid(True)
plt.show()

---

圓餅圖：plt.plot()

labels = ['juice', 'coke', 'milk', 'water']
fracs = [15, 30, 45, 10]

plt.pie(fracs, labels=labels, autopct='%1.1f%%', shadow=True, explode=(0, 0.1, 0, 0))
plt.show()

---

熱點圖：

left = ["A", "B", "C"]
down = ["1", "2.", "3"]

density = np.array([[0.8, 2.4, 2.5],
                    [2.4, 0.0, 8.0],
                    [1.1, 2.4, 0.8]])

fig, ax = plt.subplots()
im = ax.imshow(density, cmap="YlGn")

ax.set_xticks(np.arange(len(left)))
ax.set_yticks(np.arange(len(down)))
ax.set_xticklabels(left)
ax.set_yticklabels(down)

plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
         rotation_mode="anchor")

for i in range(len(left)):
    for j in range(len(down)):
        text = ax.text(j, i, density[i, j],
                       ha="center", va="center", color="k")
plt.colorbar(im)
ax.set_title("Test")
plt.show()

---

Histogram：plt.hist()

import matplotlib.mlab as mlab

data = pd.DataFrame([5,5,5,4,4,3,2,6,6,7,8])
bins = np.arange(10)

n, bins, patches = plt.hist(data, bins, normed=1, facecolor='orange', alpha=0.75) ## normed=1:機率；未加此參數會顯示個數
y = mlab.normpdf( bins, data.mean().values, data.std().values)
l = plt.plot(bins, y, 'r--', linewidth=1)

plt.xlabel('Score')
plt.ylabel('Probability')
plt.title(r'$\mathrm{Histogram\ of\ Score:}\ \mu='+ str(data.mean().values) + '\ \sigma=' + str(data.std().values) +'$')

plt.xticks(range(10))
plt.xlim([-1, 10])

plt.grid(True)
plt.grid(color='k', linestyle='--', linewidth=1)

plt.show()