书中提供的源代码为:
# 拉格朗日插值代码
import pandas as pd #导入数据分析库Pandas
import numpy as np
from scipy.interpolate import lagrange # 导入拉格朗日插值函数
input_file = '../data/catering_sale.xls' # 销量数据路径
output_file = '../tmp/sales.xls' # 输出数据路径
data = pd.read_excel(input_file) #读入数据
data[u'销量'][(data[u'销量'] < 400) | (data[u'销量'] > 5000)] = None #过滤异常值,将其变为空值
#自定义列向量插值函数
#s为列向量,n为被插值的位置,k为取前后的数据个数,默认为5
def ployinterp_column(s, n, k=5):
y = s[list(range(n-k, n)) + list(range(n+1, n+1+k))] #取数
y = y[y.notnull()] #剔除空值
return lagrange(y.index, list(y))(n) #插值并返回插值结果
#逐个元素判断是否需要插值
for i in data.columns:
for j in range(len(data)):
if (data[i].isnull())[j]: #如果为空即插值。
data[i][j] = ployinterp_column(data[i], j)
data.to_excel(output_file) #输出结果,写入文件
乍一看没什么问题,但是当我们运行的时候:
F:\anaconda\envs\sklearn-env\python.exe F:/PycharmProject/13.python_practice_of_data_analysis_and_mining-master/python_practice_of_data_analysis_and_mining-master/chapter4/demo/code/4-1_lagrange_newton_interp.py
F:\PycharmProject\13.python_practice_of_data_analysis_and_mining-master\python_practice_of_data_analysis_and_mining-master\chapter4\demo\code\4-1_lagrange_newton_interp.py:8: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
data[u'销量'][(data[u'销量'] < 400) | (data[u'销量'] > 5000)] = None # 过滤异常值,将其变为空值
Traceback (most recent call last):
File "F:\PycharmProject\13.python_practice_of_data_analysis_and_mining-master\python_practice_of_data_analysis_and_mining-master\chapter4\demo\code\4-1_lagrange_newton_interp.py", line 19, in <module>
data[i][j] = ployinterp_column(data[i], j)
File "F:\PycharmProject\13.python_practice_of_data_analysis_and_mining-master\python_practice_of_data_analysis_and_mining-master\chapter4\demo\code\4-1_lagrange_newton_interp.py", line 12, in ployinterp_column
y = s[list(range(n-k, n)) + list(range(n+1, n+1+k))] # 取数
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\series.py", line 877, in __getitem__
return self._get_with(key)
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\series.py", line 912, in _get_with
return self.loc[key]
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\indexing.py", line 895, in __getitem__
return self._getitem_axis(maybe_callable, axis=axis)
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\indexing.py", line 1113, in _getitem_axis
return self._getitem_iterable(key, axis=axis)
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\indexing.py", line 1053, in _getitem_iterable
keyarr, indexer = self._get_listlike_indexer(key, axis, raise_missing=False)
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\indexing.py", line 1266, in _get_listlike_indexer
self._validate_read_indexer(keyarr, indexer, axis, raise_missing=raise_missing)
File "F:\anaconda\envs\sklearn-env\lib\site-packages\pandas\core\indexing.py", line 1321, in _validate_read_indexer
raise KeyError(
KeyError: "Passing list-likes to .loc or [] with any missing labels is no longer supported. The following labels were missing: Int64Index([-5, -4, -3, -2, -1], dtype='int64'). See https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#deprecate-loc-reindex-listlike"
Process finished with exit code 1
我们就会看到三处报错:
1. 第一个错误原因:
data[u'销量'][(data[u'销量'] < 400) | (data[u'销量'] > 5000)] = None #过滤异常值,将其变为空值
索引出现问题,我们需要改为:
idx = (data[u'销量'] < 400) | (data[u'销量'] > 5000)
data.loc[idx, u'销量'] = None # 过滤异常值,将其变为空值# 自定义列向量插值函数
这样第一个错误原因解决!
2. 第二个错误原因:
y = s[list(range(n-k, n)) + list(range(n+1, n+1+k))] #取数
我们需要修改为:
y = s.reindex(list(range(n - k, n)) + list(range(n + 1, n + 1 + k))) # 取数
3. 第三个错误原因:
data[i][j] = ployinterp_column(data[i], j)
修改为:
data[i, j] = ployinterp_column(data[i], j)
这样错误解决!代码可以正常运行!
4. 完整版代码
# 拉格朗日插值代码
import pandas as pd # 导入数据分析库Pandas
import numpy as np
from scipy.interpolate import lagrange # 导入拉格朗日插值函数
input_file = '../data/catering_sale.xls' # 销量数据路径
output_file = '../tmp/sales.xls' # 输出数据路径
data = pd.read_excel(input_file) # 读入数据
idx = (data[u'销量'] < 400) | (data[u'销量'] > 5000)
data.loc[idx, u'销量'] = None # 过滤异常值,将其变为空值# 自定义列向量插值函数
# s为列向量,n为被插值的位置,k为取前后的数据个数,默认为5
def ployinterp_column(s, n, k=5):
y = s.reindex(list(range(n-k, n)) + list(range(n+1, n+1+k))) # 取数
y = y[y.notnull()] # 剔除空值
return lagrange(y.index, list(y))(n) # 插值并返回插值结果
# 逐个元素判断是否需要插值
for i in data.columns:
for j in range(len(data)):
if (data[i].isnull())[j]: # 如果为空即插值。
data[i,j] = ployinterp_column(data[i], j)
data.to_excel(output_file) # 输出结果,写入文件