4---直方图（matplotlib）

案例1 ----- 直方图（matplotlib）

'''
题目：假设你获取了250部电影的时长（列表a中），希望统计出这些电影时长的分布状态（比如时长为100分钟到120分钟电影的数量，出现的频率）等信息，
      你应该如何呈现这些数据？
      a=[131,  98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115,  99, 136, 126, 134,  95, 138, 117, 111,78, 132, 124, 113, 150, 110, 117,  86,  95, 144, 105, 126, 130,126, 130, 126, 116, 123, 106, 112, 138, 123,  86, 101,  99, 136,123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127,105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114,105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134,156, 106, 117, 127, 144, 139, 139, 119, 140,  83, 110, 102,123,107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133,112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135,115, 146, 137, 116, 103, 144,  83, 123, 111, 110, 111, 100, 154,136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141,120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126,114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137,  92,121, 112, 146,  97, 137, 105,  98, 117, 112,  81,  97, 139, 113,134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110,105, 129, 137, 112, 120, 113, 133, 112,  83,  94, 146, 133, 101,131, 116, 111,  84, 137, 115, 122, 106, 144, 109, 123, 116, 111,111, 133, 150]
'''
'''
绘制直方图：    plt.hist(a,20)              ------ 20为组数
绘制频率直方图：plt.hist(a,20,density=True) ------ 20为组数
'''
from matplotlib import pyplot as plt

a=[131,  98, 125, 131, 124, 139, 131, 117, 128, 108, 135, 138, 131, 102, 107, 114, 119, 128, 121, 142, 127, 130, 124, 101, 110, 116, 117, 110, 128, 128, 115,  99, 136, 126, 134,  95, 138, 117, 111,78, 132, 124, 113, 150, 110, 117,  86,  95, 144, 105, 126, 130,126, 130, 126, 116, 123, 106, 112, 138, 123,  86, 101,  99, 136,123, 117, 119, 105, 137, 123, 128, 125, 104, 109, 134, 125, 127,105, 120, 107, 129, 116, 108, 132, 103, 136, 118, 102, 120, 114,105, 115, 132, 145, 119, 121, 112, 139, 125, 138, 109, 132, 134,156, 106, 117, 127, 144, 139, 139, 119, 140,  83, 110, 102,123,107, 143, 115, 136, 118, 139, 123, 112, 118, 125, 109, 119, 133,112, 114, 122, 109, 106, 123, 116, 131, 127, 115, 118, 112, 135,115, 146, 137, 116, 103, 144,  83, 123, 111, 110, 111, 100, 154,136, 100, 118, 119, 133, 134, 106, 129, 126, 110, 111, 109, 141,120, 117, 106, 149, 122, 122, 110, 118, 127, 121, 114, 125, 126,114, 140, 103, 130, 141, 117, 106, 114, 121, 114, 133, 137,  92,121, 112, 146,  97, 137, 105,  98, 117, 112,  81,  97, 139, 113,134, 106, 144, 110, 137, 137, 111, 104, 117, 100, 111, 101, 110,105, 129, 137, 112, 120, 113, 133, 112,  83,  94, 146, 133, 101,131, 116, 111,  84, 137, 115, 122, 106, 144, 109, 123, 116, 111,111, 133, 150]

# 绘制直方图（bin_width组距   num_bin组数）
bin_width = 6                                # max(a)-min(a)-------78: 3和6的倍数，故组距可以设置为6
num_bin = (max(a)-min(a))//bin_width         # //为整除，否则直方图出错--------78/6==13.0  78//6==13    
plt.hist(a,num_bin)                           # 绘制频率直方图------plt.hist(a,num_bin,density=True)，其他代码不变

# 绘制x轴---将字符串填至x轴
_x = range(min(a), max(a)+bin_width, bin_width)  # range(78，156+6，6)----[78, 84, 90, 96, 102, 108, 114, 120, 126, 132, 138, 144, 150, 156]
plt.xticks(_x)

# 绘制网格
plt.grid()

plt.show()

case2 ---- 非原始数据不能画直方图，故条形图转换为直方图（matplotlib）

# step1
'''
绘制条形图：plt.bar(x,y,width=0.2)        # 当width=1，条形图刚好相连接
'''
'''
题目P48：
在美国2004年人口普查发现有124 million的人在离家相对较远的地方工作。根据他们从家到上班地点所需要的时间，通过抽样统计（最后一列）出了下表的数据，
这些数据能够绘制成直方图么？回答：不能绘制直方图，只能绘制条形图。因为直方图只能绘制没有统计过的原始数据。
interval = [0,5,10,15,20,25,30,35,40,45,60,90]
width = [5,5,5,5,5,5,5,5,5,15,30,60]
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]
'''
from matplotlib import pyplot as plt

interval = [0,5,10,15,20,25,30,35,40,45,60,90]                             # 12
width = [5,5,5,5,5,5,5,5,5,15,30,60]                                       # 12
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]          # 12

plt.bar(range(len(quantity)), quantity, width=1)     # 当width=1，条形图刚好相连接;     range(len(quantity))等价于range(12)

_x = range(len(quantity))    # 如果向左移0.5的长度，就刚好和网格线一致----step1
_xtick_labels = interval
plt.xticks(_x, _xtick_labels)

plt.grid()

plt.show()

# step2
'''
绘制条形图：plt.bar(x,y,width=0.2)        # 当width=1，条形图刚好相连接
'''
'''
题目P48：
在美国2004年人口普查发现有124 million的人在离家相对较远的地方工作。根据他们从家到上班地点所需要的时间，通过抽样统计（最后一列）出了下表的数据，
这些数据能够绘制成直方图么？回答：不能绘制直方图，只能绘制条形图。因为直方图只能绘制没有统计过的原始数据。
interval = [0,5,10,15,20,25,30,35,40,45,60,90]
width = [5,5,5,5,5,5,5,5,5,15,30,60]
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]
'''
from matplotlib import pyplot as plt

interval = [0,5,10,15,20,25,30,35,40,45,60,90]                             # 12
width = [5,5,5,5,5,5,5,5,5,15,30,60]                                       # 12
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]          # 12

plt.bar(range(len(quantity)), quantity, width=1)

_x = [i-0.5 for i in range(len(quantity))]    # 如果向左移0.5的长度，就刚好和网格线一致 ---- step1
_xtick_labels = interval                       # 如果给x轴再多增加1个刻度，就刚好所有的点都包含在内了 -----step2
plt.xticks(_x, _xtick_labels)

plt.grid()

plt.show()

# step3
'''
绘制条形图：plt.bar(x,y,width=0.2)        # 当width=1，条形图刚好相连接
'''
'''
题目P48：
在美国2004年人口普查发现有124 million的人在离家相对较远的地方工作。根据他们从家到上班地点所需要的时间，通过抽样统计（最后一列）出了下表的数据，
这些数据能够绘制成直方图么？回答：不能绘制直方图，只能绘制条形图。因为直方图只能绘制没有统计过的原始数据。
interval = [0,5,10,15,20,25,30,35,40,45,60,90]
width = [5,5,5,5,5,5,5,5,5,15,30,60]
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]
'''
from matplotlib import pyplot as plt

interval = [0,5,10,15,20,25,30,35,40,45,60,90]                             # 12
width = [5,5,5,5,5,5,5,5,5,15,30,60]                                       # 12
quantity = [836,2737,3723,3926,3596,1438,3273,642,824,613,215,47]          # 12

plt.bar(range(len(quantity)), quantity, width=1)

_x = [i-0.5 for i in range(13)]                      # 如果向左移0.5的长度，就刚好和网格线一致
_xtick_labels = interval + [150]                      # 如果给x轴再多增加1个刻度，就刚好所有的点都包含在内了
plt.xticks(_x, _xtick_labels)

plt.grid()

plt.show()