panda例子, 解决中文乱码问题, 繪圖

解决中文乱码问题

双击 shift 搜索 matplotlibrc
194行    font.family         : sans-serif
206行    font.sans-serif      : SimHei, Microsoft YaHei, 系统文件自带

繪圖

from pandas import read_csv
import matplotlib.pyplot as plt

df = read_csv('./gapminder.tsv', sep='\t')

global_year1 = df.groupby('year')['lifeExp'].mean()
global_year2 = df.groupby('year')['gdpPercap'].mean()

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(8, 4))

ax1.plot(global_year1)
ax2.plot(global_year2)

ax1.set_title('全球按年平均年龄')
ax2.set_title('全球按年平均GDP')

ax1.legend(['平均年龄'])
ax2.legend(['平均GDP'])
#
plt.show()

import pandas
import matplotlib.pyplot as plot

df = pandas.read_csv("./gapminder.tsv", sep='\t')

# 全球年平均寿命
global_yearly_life_expectancy = df.groupby("year")["lifeExp"].mean()

print(global_yearly_life_expectancy)
# year
# 1952    49.057620
# 1957    51.507401
# ................
# 2007    67.007423
# Name: lifeExp, dtype: float64


# 使用matplotlib可视化显示--一维表数据
global_yearly_life_expectancy.plot()

# 显示示例  或 plot.legend()   不放列表时，用默认的lifeExp
plot.legend(["平均寿命"])
# plot.legend()
# 显示标题
plot.title("全球年平均寿命")
# 显示
plot.show()

df = pandas.read_csv('./gapminder.tsv', sep='\t')

for item in zip(df.columns, df.dtypes):
    print(item)

    #output:
    # ('country', dtype('O'))
    # ('continent', dtype('O'))
    # ('year', dtype('int64'))
    # ('lifeExp', dtype('float64'))
    # ('pop', dtype('int64'))
    # ('gdpPercap', dtype('float64'))

res = dict(zip(df.columns, df.dtypes))
print(res)

#output:
# {'country': dtype('O'), 'continent': dtype('O'),
#  'year': dtype('int64'), 'lifeExp': dtype('float64'),
# 'pop': dtype('int64'), 'gdpPercap': dtype('float64')}

country = res.get('country')
print(country)

#output:
# object

平均值，出現次數？

global_year_lifeExp = df.groupby('year')['lifeExp'].mean()
# print(global_year_lifeExp)


#按year， continent分组后的  lifeExp，gdpPercap的平均值， 即每个年份下，每个大洲的  lifeExp，gdpPercap的平均值 
num_global_year_lifeExp = df.groupby(['year','continent'])[['lifeExp','gdpPercap']].mean()
# print(num_global_year_lifeExp)


# print(num_global_year_lifeExp.reset_index())  数据还原到原来格式


# 按continent分组后， 每个country下出现的次数统计
print(df.groupby('continent')['country'].nunique())

一，二维数据

print(df.loc[0:3, ['year', 'gdpPercap']])  #str loc   得4行
print(df.iloc[0:3, [2, 5]])                #int loc   得3行
#--------------------------------------

# x, y 轴连续数
print(df.iloc[0:6,3:6])       # x, y 轴连续数，int loc

# x, y 轴的非连续数
print(df.loc[:,['country','year']])

print(df.iloc[:,[2,6]].head())

print(df.loc[0,['year']])  #单行Series
print(type(df.loc[0,['year']])) #<class 'pandas.core.series.Series'>

haha = df['country']
print(haha)
# ----many-------    Name: country, Length: 1704, dtype: object


print(df.shape)
#  (1704, 6)



print(df.tail(3))
print(df.tail(100))

print(df.head())
print(df.head(18))

print(df.loc[0])
# country      Afghanistan
# continent           Asia
# year                1952
# lifeExp           28.801
# pop              8425333
# gdpPercap        779.445
# Name: 0, dtype: object


print(df.loc[3])
# country      Afghanistan
# continent           Asia
# year                1967
# lifeExp            34.02
# pop             11537966
# gdpPercap        836.197
# Name: 3, dtype: object


print(df.iloc[-1])     # last = df.shape[0]-1,  print(df.loc[last])

# country      Zimbabwe
# continent      Africa
# year             2007
# lifeExp        43.487
# pop          12311143
# gdpPercap     469.709
# Name: 1703, dtype: object



print(df.iloc[[0,-2,-1]])   ## last = df.shape[0]-1,  print(df.iloc[[0,2,last]])

#           country continent  year  lifeExp       pop   gdpPercap
# 0     Afghanistan      Asia  1952   28.801   8425333  779.445314
# 1702     Zimbabwe    Africa  2002   39.989  11926563  672.038623
# 1703     Zimbabwe    Africa  2007   43.487  12311143  469.709298

#得到year,pop 的....n行
subset = df.loc[0:3,["year","pop"]]
# subset = df.loc[:,["year","pop"]]

#得到2,4和最后一列数据
subset2 = df.iloc[:,[2,4,-1]]
# print(subset2)

# #得到下标是3到6的列
subset3 = df.iloc[:,3:6]
print(subset3.head())
#    lifeExp       pop   gdpPercap
# 0   28.801   8425333  779.445314
# 1   30.332   9240934  820.853030
# 2   31.997  10267083  853.100710
# 3   34.020  11537966  836.197138
# 4   36.088  13079460  739.981106