【稳住，can win】数据分析实例

统计911不同类型的紧急情况的次数

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

file_path = "DataAnalysis/911.csv"
df = pd.read_csv(file_path)
# 获取分类
temp_list = df["title"].str.split(":").tolist()
cate_list = list(set([i[0] for i in temp_list]))
# 构造全为0的数组
zero_df = pd.DataFrame(np.zeros((df.shape[0], len(cate_list))), columns=cate_list)
# 赋值
for cate in cate_list:
    zero_df[cate][df["title"].str.contains(cate)] = 1

sum_ret = zero_df.sum(axis=0)

统计911不同月份不同类型紧急电话的次数的变化情况

#统计出911数据中不同月份不同类型电话次数的变化情况
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，并设置成索引
df = pd.read_csv("DataAnalysis/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]
df["cate"] = pd.DataFrame(np.array(cate_list).reshape((df.shape[0], 1)))
df.set_index("timeStamp", inplace=True)

plt.figure(figsize=(20,8), dpi=80)
# 分组
for group_name, group_data in df.groupby(by="cate"):
    # 对不同分类进行绘图
    count_by_month = group_data.resample("M").count()["title"]

    #画图
    _x = count_by_month.index
    _y = count_by_month.values
    _x = [i.strftime("%Y/%m/") 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()

统计PM2.5

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

file_path = "DataAnalysis/PM2.5/BeijingPM20100101_20151231.csv"
df = pd.read_csv(file_path)

# 把分开的时间字符串通过periodIndex的方法转换为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

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

# 进行下采样
data = df.resample("7D").mean()

# 处理缺失数据
data = df["PM_US Post"].dropna()
data_china = df["PM_Dongsi"].dropna()


# 画图
_x = data.index
_x = [i.strftime("%Y%m%d") for i in _x]
_y = data.values

_x_china = [i.strftime("%Y%m%d") for i in data_china.index]
_y_china = data_china.values

plt.figure(figsize=(20,8), dpi=80)
plt.plot(range(0, len(_x), 10), _y[::10], label="US Post")
plt.plot(range(0, len(_x_china), 10), _y_china[::10], label="CN Post")

plt.xticks(range(0, len(_x), 10), list(_x)[::10], rotation=45)
plt.legend(loc="best")
plt.show()