Python:多元线性回归:statsmodels.formula.api.ols()

Question

我试图从温度，湿度等各种因素中找到总功率的依赖性，并具有以下代码：

from functools import reduce
dfs=[df1,df2,df4,df7]
df_final = reduce(lambda left,right:pd.merge(left,right,left_index=True,right_index=True), dfs)
df_final=df_final.drop(["0_x","0_y",0,4],1)
df_final.columns=["OT","HP","H","TP"]

# df_final.shape output is (8790, 4)
import statsmodels.formula.api as smf
lm = smf.ols(formula='TP ~ OT+HP+H',data=df_final).fit()
lm.summary()

输出：

ValueError                                Traceback (most recent call last)
<ipython-input-45-c09782ec7959> in <module>()
  3 lm = smf.ols(formula='TP ~ OT+HP+H',data=df_final).fit()
  4 
----> 5 lm.summary()
C:Anaconda3libsite-packagesstatsmodelsregressionlinear_model.py in summary(self, yname, xname, title, alpha)
1948             top_left.append(('Covariance Type:', [self.cov_type]))
1949 
-> 1950         top_right = [('R-squared:', ["%#8.3f" % self.rsquared]),
1951                      ('Adj. R-squared:', ["%#8.3f" % self.rsquared_adj]),
1952                      ('F-statistic:', ["%#8.4g" % self.fvalue] ),
C:Anaconda3libsite-packagesstatsmodelstoolsdecorators.py in __get__(self, obj, type)
 92         if _cachedval is None:
 93             # Call the "fget" function
---> 94             _cachedval = self.fget(obj)
 95             # Set the attribute in obj
 96 #            print("Setting %s in cache to %s" % (name, _cachedval))
C:Anaconda3libsite-packagesstatsmodelsregressionlinear_model.py in rsquared(self)
1179     def rsquared(self):
1180         if self.k_constant:
-> 1181             return 1 - self.ssr/self.centered_tss
1182         else:
1183             return 1 - self.ssr/self.uncentered_tss
C:Anaconda3libsite-packagesstatsmodelstoolsdecorators.py in __get__(self, obj, type)
 92         if _cachedval is None:
 93             # Call the "fget" function
 ---> 94             _cachedval = self.fget(obj)
 95             # Set the attribute in obj
 96 #            print("Setting %s in cache to %s" % (name, _cachedval))
C:Anaconda3libsite-packagesstatsmodelsregressionlinear_model.py in ssr(self)
1151     def ssr(self):
1152         wresid = self.wresid
-> 1153         return np.dot(wresid, wresid)
1154 
1155     @cache_readonly
ValueError: shapes (8790,4294) and (8790,4294) not aligned: 4294 (dim 1) != 8790 (dim 0)

我不知道为什么我在这里获得形状不匹配。我什至尝试使用较小的数据集尝试过，但仍有类似的错误。感谢您阅读。关于如何有效分享我的ipython笔记本的任何评论也将有所帮助。

Answer 1

我的数据列之一是字符串而不是float，因此引发了此错误。