1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

import pandas as pd
import numpy as np

import warnings
warnings.filterwarnings('ignore')

# read excel file 
df = pd.read_excel('catering_sale.xls',index_col='日期')
print(df.head())

# Generate descriptive statitsticsb
descriptive_stats = df.describe(include='all').transpose()

# Find any missing values in dataframe
missing_values = df['销量'].isnull().sum()

# Print the results 
print(descriptive_stats)
print(missing_values)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

                销量
日期                
2015-03-01    51.0
2015-02-28  2618.2
2015-02-27  2608.4
2015-02-26  2651.9
2015-02-25  3442.1
    count       mean         std   min       25%      50%       75%      max
销量  200.0  2755.2147  751.029772  22.0  2451.975  2655.85  3026.125  9106.44
1

1
2
3
4
5
6
7

df=pd.read_excel('catering_sale.xls',index_col='日期')
df=df[(df['销量']>400)&(df['销量']<5000)]
descriptive_stats = df.describe(include='all').transpose()
descriptive_stats['range']=descriptive_stats['max']-descriptive_stats['min']
descriptive_stats['var']=descriptive_stats['std']/descriptive_stats['mean']
descriptive_stats['dis']=descriptive_stats['75%']-descriptive_stats['25%']
descriptive_stats

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

# 画出数据的箱线图
import matplotlib.pyplot as plt  # 导入图像库

plt.rc('font', family='sans-serif')

plt.figure()
p = df.boxplot(return_type='dict')  # 画箱线图, 处理异常值
x = p['fliers'][0].get_xdata() # 'flies'即为异常值的标签
y = p['fliers'][0].get_ydata()
y.sort()

for index in range(len(x)):
  if index > 0:
    plt.annotate(y[index], xy = (x[index], y[index]), xytext=(x[index]+0.05 -0.8/(y[index]-y[index-1]), y[index]))
  else:
    plt.annotate(y[index], xy = (x[index], y[index]), xytext=(x[index]+0.08, y[index]))

plt.title('3322-li箱型图',fontsize=12)
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

# Read in data and designate 'Date' column as index 
data = pd.read_excel("catering_fish_congee.xls",names=['date','sale'])

# Create bins (0-500, 500-1000, etc.)
bins = [0,500,1000,1500,2000,2500,3000,3500,4000]
labels = ['[0,500)','[500,1000)','[1000,1500)','[1500,2000)',
       '[2000,2500)','[2500,3000)','[3000,3500)','[3500,4000)']

# Group data according to bins and compute the number of instances
data['sale分层'] = pd.cut(data.sale, bins, labels=labels)  # Binning
aggResult = data.groupby(by=['sale分层'])['sale'].agg(np.size)         # Aggregration
print(aggResult)

# Calculate percentage of each bin and show result
pAggResult = round(aggResult/aggResult.sum(), 2, ) * 100
print(pAggResult)

# Plot graph to visualize result
plt.figure(figsize=(10,6))  # Set figure size
pAggResult.plot(kind='bar',width=0.8,fontsize=10)  # Draw frequency histogram
plt.title('3322-li季度销售额频率分布直方图',fontsize=12) # Set chart title
plt.xticks(rotation=45)
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

sale分层
[0,500)        28
[500,1000)     20
[1000,1500)    12
[1500,2000)    12
[2000,2500)     8
[2500,3000)     3
[3000,3500)     4
[3500,4000)     3
Name: sale, dtype: int64
sale分层
[0,500)        31.0
[500,1000)     22.0
[1000,1500)    13.0
[1500,2000)    13.0
[2000,2500)     9.0
[2500,3000)     3.0
[3000,3500)     4.0
[3500,4000)     3.0
Name: sale, dtype: float64

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

import pandas as pd
import matplotlib.pyplot as plt
data = pd.read_excel('catering_dish_profit.xls')  # 读取数据

# Set figure size 
plt.figure(figsize=(10,6))

# Draw pie chart 
x = data['盈利']
labels = data['菜品名']
plt.pie(x, labels=labels)

# Set title and make pie chart look nice
plt.title('3322-li菜品销售量分布（饼图）', fontsize=15)
plt.axis('equal')

1

(-1.0999995230582924, 1.09999997728849, -1.0999999973110348, 1.099999968474505)

1
2
3
4
5
6
7
8
9

x = data['菜品名']
y = data['盈利']
plt.figure(figsize=(10,6))  # 设置图框大小尺寸
plt.title('3322-li菜品销售量分布（条形图）', fontsize=15)  
plt.bar(x, y, color='g') # 绘制饼图
plt.rcParams['font.sans-serif'] = ['SimHei']   
plt.xlabel('菜品')	# 设置 x 轴标签 
plt.ylabel('销量')	# 设置 y 轴标签 
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

#部门之间销售金额比较
data = pd.read_excel("dish_sale.xls")  # 读取数据

plt.figure(figsize=(10,6))  # 设置图框大小尺寸

plt.plot(data['月份'],data['A部门'],color='skyblue',label='A部门',marker='o')
plt.plot(data['月份'],data['B部门'],color='red',label='B部门',marker='*')
plt.plot(data['月份'],data['C部门'],color='yellow',label='C部门',marker='s')

plt.legend()#显示图例
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.title('3322-li部门之间销售金额比较',fontsize=15)
plt.ylabel('销售额（万元）')
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

#B部门各年份之间销售金额比较
data = pd.read_excel("dish_sale_b.xls")  # 读取数据

plt.figure(figsize=(10,6))  # 设置图框大小尺寸

# Set parameters
line_width = 2
colors = ["green", "yellow", "purple"]
markers = ["o", "*", "s"]
labels = ["2012年", "2013年", "2014年"]

for i, year in enumerate(["2012年", "2013年", "2014年"]):
    plt.plot(data['月份'], data[year], color=colors[i], 
    label=labels[i], marker=markers[i], linewidth=line_width)

plt.legend()#显示图例
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.title('3148-TangB部门各年份之间销售金额比较',fontsize=15)
plt.ylabel('销售额（万元）')
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

df_normal = pd.read_csv("user.csv") # 读入数据
plt.figure(figsize=(10,6))
plt.plot(df_normal["Date"],df_normal["Eletricity"],color='green')
plt.xlabel("日期")
plt.ylabel("每日电量")

# 设置x轴刻度间隔
x_major_locator = plt.MultipleLocator(7)
ax = plt.gca()
ax.xaxis.set_major_locator(x_major_locator)
plt.show()  # 展示图片

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

df_steal = pd.read_csv("Steal user.csv")
plt.figure(figsize=(10, 6))
plt.plot(df_steal["Date"],df_steal["Eletricity"],color='yellow')
plt.xlabel("日期")
plt.ylabel("日期")

# 设置x轴刻度间隔
x_major_locator = plt.MultipleLocator(7)
ax = plt.gca()
ax.xaxis.set_major_locator(x_major_locator)
plt.title("3322li-窃电用户电量趋势",fontsize=15)
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.show()  # 展示图片

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

import pandas as pd

data = pd.read_excel('catering_dish_profit.xls', index_col = u'菜品名')
data = data['盈利'].copy()
data.sort_values(ascending = False)

plt.figure()
data.plot(kind='bar')
plt.ylabel('盈利（元）')#左侧y轴，右侧y轴
p = 1.0*data.cumsum()/data.sum()
p.plot(color = 'r', secondary_y = True, style = '-o',linewidth = 2)
plt.annotate(format(p[6], '.4%'), xy = (6, p[6]), xytext=(6*0.9, p[6]*0.9), arrowprops=dict(arrowstyle="->", connectionstyle="arc3,rad=.8")) #添加注释，即85%处的标记。这里包括了指定箭头样式。
plt.ylabel('盈利（比例）')
plt.title("3322li-菜品盈利数据帕累托图",fontsize=15)
plt.show()

1
2
3
4
5
6

import pandas as pd
data = pd.read_excel('catering_sale_all.xls', index_col = u'日期') #读取数据，指定“日期”列为索引列
 #相关系数矩阵，即给出了任意两款菜式之间的相关系数
data.corr()
pd.options.display.float_format = '{:,.2f}'.format ## 指定小数位数
data.corr()

1
2
3

 #只显示“百合酱蒸凤爪”与其他菜式的相关系数
print(data.corr()[u'百合酱蒸凤爪'])
data['百合酱蒸凤爪'].corr(data['翡翠蒸香茜饺']) #计算“百合酱蒸凤爪”与“翡翠蒸香茜饺”的相关系数

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

百合酱蒸凤爪     1.00
翡翠蒸香茜饺     0.01
金银蒜汁蒸排骨    0.02
乐膳真味鸡      0.46
蜜汁焗餐包      0.10
生炒菜心       0.31
铁板酸菜豆腐     0.20
香煎韭菜饺      0.13
香煎罗卜糕     -0.09
原汁原味菜心     0.43
Name: 百合酱蒸凤爪, dtype: float64

0.009205803051836475

1
2
3
4

import pandas as pd 
import numpy as np
D = pd.DataFrame (np.random. randn (6, 5) ) #产生6X5随机矩阵
D.cov() #计算协方差矩阵

1
2
3
4
5
6
7
8
9

import matplotlib.pyplot as plt
import numpy as np
x = np.linspace(0,2*(np.pi))
y1 = np.sin(x)
y2 = np.cos(x)
plt.figure()
plt.plot(x,y1,'r-o')
plt.plot(x,y2,'b-*')
plt.legend("sin(x)")

1

<matplotlib.legend.Legend at 0x294574e3460>

1
2
3
4
5
6
7
8
9

import matplotlib.pyplot as plt #导入作图库
# The slices will be ordered and plotted counter-clockwise.
labels = ' Frogs', 'Hogs', ' Dogs', 'Logs' , #定义标签
sizes = [15, 30, 45, 10] # 每一块的比例
colors = [ 'yellowgreen', 'gold', 'lightskyblue', 'lightcoral' ] #每一块的颜色
explode = (0, 0.1, 0, 0) #突出显示，这里仅仅突出显示第二块(即'Hogs')
plt.pie(sizes, explode=explode, labels=labels, colors=colors, autopct='%1.1f%%',shadow=True, startangle=90)
plt .axis ('equal') #显示为圆(避免比例压缩为椭圆)
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

import matplotlib.pyplot as plt  # 导入作图库
import numpy as np
import pandas as pd

plt.figure(figsize=(8,6))
x = pd. Series (np.exp (np. arange (20) ) ) #原始数据
plt.subplot(1,2,1)
x.plot (label = '原始数据图',legend = True,color='lightskyblue')
plt.title('3322li',fontsize=15)
plt.subplot(1,2,2)
x.plot (logy = True,label = '原始数据图',legend = True,color='lightcoral') 
plt.show()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

import numpy as np
import matplotlib.pyplot as plt

# 构造数据
x = np.arange(10)
y = 2.5 * np.sin(x / 20 * np.pi)
# 构造一维数组
yerr1 = np.linspace(0.05, 0.2, 10)
# 构造(2,N)结构的数组
yerr2 = np.random.rand(2,10)

# 浮点值，所有点统一对称误差
plt.errorbar(x, y, yerr=0.5)
# 一维数组，每个点分别根据数组对应元素设置对称误差
plt.errorbar(x, y - 1, yerr=yerr1)
# (2,N)结构数组，每个点分别根据数组设置误差
# 第一行对应每个点的负误差，第二行对应每个点的正误差
plt.errorbar(x, y - 2, yerr=yerr2)

plt.show()