pandas案例

pandas时间序列

统计出911数据中不同月份电话次数的

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt


df = pd.read_csv("./911.csv")


df["timeStamp"] = pd.to_datetime(df["timeStamp"])

df.set_index("timeStamp",inplace=True)


#统计出911数据中不同月份电话次数的
count_by_month = df.resample("M").count()["title"]
print(count_by_month)

#画图
_x = count_by_month.index
_y = count_by_month.values

# for i in _x:
#     print(dir(i))
#     break
_x = [i.strftime("%Y%m%d") for i in _x]

plt.figure(figsize=(20,8),dpi=80)

plt.plot(range(len(_x)),_y)

plt.xticks(range(len(_x)),_x,rotation=45)

plt.show()

911数据中不同月份不同类型的电话的次数的变化情况

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt

#把时间字符串转为时间类型设置为索引
df = pd.read_csv("./911.csv")
df["timeStamp"] = pd.to_datetime(df["timeStamp"])

#添加列，表示分类
temp_list = df["title"].str.split(": ").tolist()
cate_list = [i[0] for i in temp_list]
# print(np.array(cate_list).reshape((df.shape[0],1)))
df["cate"] = pd.DataFrame(np.array(cate_list).reshape((df.shape[0],1)))

df.set_index("timeStamp",inplace=True)

print(df.head(1))

plt.figure(figsize=(20, 8), dpi=80)

#分组
for group_name,group_data in df.groupby(by="cate"):

    #对不同的分类都进行绘图
    count_by_month = group_data.resample("M").count()["title"]

    # 画图
    _x = count_by_month.index
    print(_x)
    _y = count_by_month.values

    _x = [i.strftime("%Y%m%d") for i in _x]

    plt.plot(range(len(_x)), _y, label=group_name)


plt.xticks(range(len(_x)), _x, rotation=45)
plt.legend(loc="best")
plt.show()

PM2.5随时间变化

import pandas as pd
from matplotlib import  pyplot as plt
file_path = "./PM2.5/BeijingPM20100101_20151231.csv"

df = pd.read_csv(file_path)
# print(df.info())

#把分开的时间字符串通过periodIndex的方法转化为pandas的时间类型
period = pd.PeriodIndex(year=df["year"],month=df["month"],day=df["day"],hour=df["hour"],freq="H")
df["datetime"] = period
print(df.head(10))

#把datetime 设置为索引
df.set_index("datetime",inplace=True)

#进行降采样
df = df.resample("7D").mean()
print(df.head())
#处理缺失数据，删除缺失数据
print(df["PM_US Post"])


data  =df["PM_US Post"].dropna()#删除该列中Nan的行
data_china = df["PM_Nongzhanguan"].drop()
print(df['PM_Nongzhanguan'].tail(20))#查看该列末尾的20条数据
print(df['PM_US Post'].tail(20))#查看该列末尾的20条数据

print(data_china.head(100))
#画图
_x = data.index
_x = [i.strftime("%Y%m%d") for i in _x]
_x_china = [i.strftime("%Y%m%d") for i in data_china.index]
print(len(_x_china),len(_x_china))
_y = data.values
_y_china = data_china.values


plt.figure(figsize=(20,8),dpi=80)

plt.plot(range(len(_x)),_y,label="US_POST",alpha=0.7)
plt.plot(range(len(_x_china)),_y_china,label="CN_POST",alpha=0.7)

plt.xticks(range(0,len(_x_china),10),list(_x_china)[::10],rotation=45)

plt.legend(loc="best")

plt.show()