情景描述
有一家专业从事煤矿安全监控和预防的公司。最近该公司承接了某煤井的井下监控工作，需要通过采集井下温度，井下湿度以及气体涌出量来评估和监控井下的环境和状况。
任务实施
1.读取数据
python
import numpy as np
temperature_str = np.loadtxt(
"ug_detect.csv",
delimiter=",",
skiprows=1,
usecols=(1),
dtype=bytes
)
humidity_str = np.loadtxt(
"ug_detect.csv",
delimiter=",",
skiprows=1,
usecols=(2),
dtype=bytes
)
gas_str = np.loadtxt(
"ug_detect.csv",
delimiter=",",
skiprows=1,
usecols=(3),
dtype=bytes
)
co_str = np.loadtxt(
"ug_detect.csv",
delimiter=",",
skiprows=1,
usecols=(4),
dtype=bytes
)
print(temperature_str)
print(humidity_str)
print(gas_str)
print(co_str)
2.缺失值和异常值处理
缺失值处理
python
def conver_data(array_str,flag):
array = np.zeros(len(array_str))
# 类型转换+缺失值处理
for i in range(len(array_str)):
item = array_str[i]
if item != b'': # 如果当前元素为空
item = float(item)
if flag == 1:
if item > 50:
item = None
elif flag == 2:
if item > 200:
item = None
elif flag == 3 or flag == 4:
if item > 100:
item = None
else: # 如果为空
item = None # 将缺失值填充为无效值
array[i] = item
return array
temperature = conver_data(temperature_str,1)
humidity = conver_data(humidity_str,2)
gas = conver_data(gas_str,3)
co = conver_data(co_str,4)
处理nan值
python
def bisec(array):
for i in range(len(array)):
if np.isnan(array[i]):
if i == len(array) - 1: #最后一个元素
array[i] =array[i - 1]
elif i == 0: # 第一个元素
array[i] = array[i + 1]
else:
array[i] = (array[i - 1] + array[i + 1]) / 2
return array
temperature = bisec(temperature)
humidity = bisec(humidity)
gas = bisec(gas)
co = bisec(co)
