x连续变量 y 分类变量 logit图 手工分箱
from woe import WoE
woe = WoE(v_type='d')
woe.fit(auto.age_group,auto.Loss)
fig = woe.plot([8,5])
plt.show(fig)
地图统计
from pyecharts import Map
gdp_data = list(zip(gdp[gdp.Year == 2014].loc[:,'Prov'],gdp[gdp.Year == 2014].loc[:,'GDP']))
attr, value = Map.cast(gdp_data)
GDP_max = gdp[gdp.Year == 2014].GDP.max()
GDP_min = gdp[gdp.Year == 2014].GDP.min()
map = Map('各省GDP', width = 1200, height = 600)
map.add('', attr, value, maptype = 'china', is_visualmap = True, visual_range=[GDP_min, GDP_max],
visual_text_color = '#000', is_label_show = True)
map.render()
from pyecharts import Map
snd_price = list(zip(snd.price.groupby(snd.district).mean().index,
snd.price.groupby(snd.district).mean().values))
attr, value = Map.cast(snd_price)
min_ = snd.price.groupby(snd.dist).mean().min()
max_ = snd.price.groupby(snd.dist).mean().max()
map = Map('北京各区房价', width = 1200, height = 600)
map.add('', attr, value, maptype = '北京', is_visualmap = True, visual_range=[min_, max_],
visual_text_color = '#000', is_label_show =True)
map.render()
堆叠柱形图
def stack2dim(raw, i, j, rotation = 0, location = 'upper left'):
'''
此函数是为了画两个维度标准化的堆积柱状图
要求是目标变量j是二分类的
raw为pandas的DataFrame数据框
i、j为两个分类变量的变量名称，要求带引号，比如"school"
rotation：水平标签旋转角度，默认水平方向，如标签过长，可设置一定角度，比如设置rotation = 40
location：分类标签的位置，如果被主体图形挡住，可更改为'upper left'
'''
import math
data_raw = pd.crosstab(raw[i], raw[j])
data = data_raw.div(data_raw.sum(1), axis=0) # 交叉表转换成比率，为得到标准化堆积柱状图
# 计算x座标，及bar宽度
createVar = locals()
x = [0] #每个bar的中心x轴座标
width = [] #bar的宽度
k = 0
for n in range(len(data)):
# 根据频数计算每一列bar的宽度
createVar['width' + str(n)] = data_raw.sum(axis=1)[n] / sum(data_raw.sum(axis=1))
width.append(createVar['width' + str(n)])
if n == 0:
continue
else:
k += createVar['width' + str(n - 1)] / 2 + createVar['width' + str(n)] / 2 + 0.05
x.append(k)
# 以下是通过频率交叉表矩阵生成一列对应堆积图每一块位置数据的数组，再把数组转化为矩阵
y_mat = []
n = 0
for p in range(data.shape[0]):
for q in range(data.shape[1]):
n += 1
y_mat.append(data.iloc[p, q])
if n == data.shape[0] * 2:
break
elif n % 2 == 1:
y_mat.extend([0] * (len(data) - 1))
elif n % 2 == 0:
y_mat.extend([0] * len(data))
y_mat = np.array(y_mat).reshape(len(data) * 2, len(data))
y_mat = pd.DataFrame(y_mat) # bar图中的y变量矩阵，每一行是一个y变量
# 通过x，y_mat中的每一行y，依次绘制每一块堆积图中的每一块图
createVar = locals()
for row in range(len(y_mat)):
createVar['a' + str(row)] = y_mat.iloc[row, :]
if row % 2 == 0:
if math.floor(row / 2) == 0:
label = data.columns.name + ': ' + str(data.columns[row])
plt.bar(x, createVar['a' + str(row)],
width=width[math.floor(row / 2)], label='not Loss', color='#5F9EA0')
else:
plt.bar(x, createVar['a' + str(row)],
width=width[math.floor(row / 2)], color='#5F9EA0')
elif row % 2 == 1:
if math.floor(row / 2) == 0:
label = data.columns.name + ': ' + str(data.columns[row])
plt.bar(x, createVar['a' + str(row)], bottom=createVar['a' + str(row - 1)],
width=width[math.floor(row / 2)], label='Loss', color='#8FBC8F')
else:
plt.bar(x, createVar['a' + str(row)], bottom=createVar['a' + str(row - 1)],
width=width[math.floor(row / 2)], color='#8FBC8F')
plt.title(j + ' vs ' + i)
group_labels = [data.index.name + ': ' + str(name) for name in data.index]
plt.xticks(x, group_labels, rotation = rotation)
plt.ylabel(j)
plt.legend(shadow=True, loc=location)
plt.show()
stack2dim(snd, i="subway", j="school")