def show_user_age_pie():
map = userDs.get_country_user_age_data()
data =[]
labels =[]
for k in map:
labels.append(k)
data.append(map[k])
colors = 'yellowgreen', 'gold', 'lightskyblue', 'lightcoral', 'orange', 'yellow', 'red', 'pink'
explode = 0, 0, 0, 0, 0.1, 0, 0
font = FontProperties(fname='/Library/Fonts/Songti.ttc', size=10)
pie = plt.pie(data, labels=labels, explode=explode, colors=colors, autopct='%1.1f%%', shadow=False, startangle=40,
textprops={'fontsize': 12})
# 解决标题中文乱码
plt.title("keep用户年龄分布", fontproperties=font)
# 解决乱码问题
for font in pie[1]:
font.set_fontproperties(matplotlib.font_manager.FontProperties(fname='/Library/Fonts/Songti.ttc'))
plt.axis('equal')
# plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
#
# plt.rcParams['font.family']=['Arial Black']
plt.show()
def caculateWordFrequency():
'''
统计词频，画柱形图、饼状图
:return:
'''
global wordList, wordFrequency
## 统计词频，储存在wordFrequency dict里面
for word in wordList:
if word in wordFrequency.keys():
wordFrequency[word] += 1
else:
wordFrequency[word] = 1
## 按value值排序
items = wordFrequency.items()
sortedItems = [[item[1], item[0]] for item in items]
sortedItems.sort() ## 顺序
sortedItems.reverse() ## 降序
## 取前30个，画柱形图
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc",
size=14) ##字体设置
X_labels = [sortedItems[i][1] for i in range(0, 30)]
Y = [sortedItems[i][0] for i in range(0, 30)]
X = range(len(X_labels))
fig = plt.figure()
plt.bar(X, Y, color="green")
plt.xticks(X, X_labels, fontproperties=font)
plt.xlabel("X-axis")
plt.ylabel("Y-axis")
plt.title("TOP 30th words")
plt.show()
## 取前30个，画饼状图
labels = [sortedItems[i][1] for i in range(0, len(sortedItems))]
### 求比例
totalNum = 0
rates = []
for sortedItem in sortedItems:
totalNum += sortedItem[0]
for i in range(0, len(sortedItems)):
rate = sortedItems[i][0] / totalNum * 100
rate = round(rate, 10)
rates.append(rate)
### 取前30个词语
labels = labels[0:30]
rates = rates[0:30]
### 作图
explode = [0] * 30
explode[0] = explode[1] = 0.1 ## 突出第一、二个
fig = plt.figure()
plt.axes(aspect=1)
patches, l_text, p_text = plt.pie(x=rates,
labels=labels,
explode=explode,
autopct='%3.1f %%',
shadow=True,
labeldistance=1.1,
startangle=90,
pctdistance=0.8)
### 中文显示问题
for font in l_text:
font.set_fontproperties(
FontProperties(fname=r"c:\windows\fonts\simsun.ttc"))
plt.show()
def caculateWordFrequency():
'''
统计词频，画柱形图、饼状图
:return:
'''
global wordList,wordFrequency
## 统计词频，储存在wordFrequency dict里面
for word in wordList:
if word in wordFrequency.keys():
wordFrequency[word] += 1
else:
wordFrequency[word] = 1
## 按value值排序
items = wordFrequency.items()
sortedItems = [ [item[1],item[0]] for item in items ]
sortedItems.sort() ## 顺序
sortedItems.reverse() ## 降序
## 取前30个，画柱形图
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14) ##字体设置
X_labels = [ sortedItems[i][1] for i in range(0,30) ]
Y = [ sortedItems[i][0] for i in range(0,30) ]
X = range(len(X_labels))
fig = plt.figure()
plt.bar(X, Y, color="green")
plt.xticks(X, X_labels,fontproperties=font)
plt.xlabel("X-axis")
plt.ylabel("Y-axis")
plt.title("TOP 30th words")
plt.show()
## 取前30个，画饼状图
labels = [ sortedItems[i][1] for i in range(0,len(sortedItems)) ]
### 求比例
totalNum = 0
rates = []
for sortedItem in sortedItems:
totalNum += sortedItem[0]
for i in range(0,len(sortedItems)):
rate = sortedItems[i][0] / totalNum * 100
rate = round(rate,10)
rates.append(rate)
### 取前30个词语
labels = labels[0:30]
rates = rates[0:30]
### 作图
explode = [0] * 30
explode[0] = explode[1] = 0.1 ## 突出第一、二个
fig = plt.figure()
plt.axes(aspect=1)
patches,l_text,p_text = plt.pie(
x=rates,
labels=labels,
explode=explode,
autopct='%3.1f %%',
shadow=True,
labeldistance=1.1,
startangle=90,
pctdistance=0.8
)
### 中文显示问题
for font in l_text:
font.set_fontproperties(FontProperties(fname=r"c:\windows\fonts\simsun.ttc"))
plt.show()
def show_user_age_pie():
cursor.execute(birthday_sql)
result = cursor.fetchall()
tag_60s = '50，60后'
tag_70s = '70后'
tag_80s = '80后'
tag_85s = '85后'
tag_90s = '90后'
tag_95s = '95后'
tag_00s = '00后'
labels = tag_60s, tag_70s, tag_80s, tag_85s, tag_90s, tag_95s, tag_00s
map = {
tag_60s: 0,
tag_70s: 0,
tag_80s: 0,
tag_85s: 0,
tag_90s: 0,
tag_95s: 0,
tag_00s: 0
}
for item in result:
bd = item['bd']
count = item['count']
if 1950 <= bd < 1970:
map[tag_60s] = map[tag_60s] + count
pass
elif 1970 <= bd < 1980:
map[tag_70s] = map[tag_70s] + count
pass
elif 1980 <= bd < 1985:
map[tag_80s] = map[tag_80s] + count
elif 1985 <= bd < 1990:
map[tag_85s] = map[tag_85s] + count
pass
elif 1990 <= bd < 1995:
map[tag_90s] = map[tag_90s] + count
pass
elif 1995 <= bd < 2000:
map[tag_95s] = map[tag_95s] + count
pass
elif 2000 <= bd < 2010:
map[tag_00s] = map[tag_00s] + count
pass
pass
sizes = [
map[tag_60s], map[tag_70s], map[tag_80s], map[tag_85s], map[tag_90s],
map[tag_95s], map[tag_00s]
]
colors = 'yellowgreen', 'gold', 'lightskyblue', 'lightcoral', 'orange', 'yellow', 'red', 'pink'
explode = 0, 0, 0, 0, 0, 0.1, 0, 0
font = FontProperties(fname='/Library/Fonts/Songti.ttc', size=10)
pie = plt.pie(sizes,
labels=labels,
explode=explode,
colors=colors,
autopct='%1.1f%%',
shadow=False,
startangle=40,
textprops={'fontsize': 12})
# 解决标题中文乱码
plt.title("keep用户年龄分布", fontproperties=font)
# 解决乱码问题
for font in pie[1]:
font.set_fontproperties(
matplotlib.font_manager.FontProperties(
fname='/Library/Fonts/Songti.ttc'))
plt.axis('equal')
# plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
#
# plt.rcParams['font.family']=['Arial Black']
plt.show()
