我一直试图建立一个非常简单的初始模型预测的罚款养老院可能期望基于其位置支付的金额。
这是我的类定义
#initial model to predict the amount of fines a nursing home might expect to pay based on its location
from sklearn.base import BaseEstimator, RegressorMixin, TransformerMixin
class GroupMeanEstimator(BaseEstimator, RegressorMixin):
#defines what a group is by using grouper
#initialises an empty dictionary for group averages
def __init__(self, grouper):
self.grouper = grouper
self.group_averages = {}
#Any calculation I require for my predict method goes here
#Specifically, I want to groupby the group grouper is set by
#I want to then find out what is the mean penalty by each group
#X is the data containing the groups
#Y is fine_totals
#map each state to its mean fine_tot
def fit(self, X, y):
#Use self.group_averages to store the average penalty by group
Xy = X.join(y) #Joining X&y together
state_mean_series = Xy.groupby(self.grouper)[y.name].mean() #Creating a series of state:mean penalties
#populating a dictionary with state:mean key:value pairs
for row in state_mean_series.iteritems():
self.group_averages[row[0]] = row[1]
return self
#The amount of fine an observation is likely to receive is based on his group mean
#Want to first populate the list with the number of observations
#For each observation in the list, what is his group and then set the likely fine to his group mean.
#Return the list
def predict(self, X):
dictionary = self.group_averages
group = self.grouper
list_of_predictions = [] #initialising a list to store our return values
for row in X.itertuples(): #iterating through each row in X
prediction = dictionary[row.STATE] #Getting the value from group_averages dict using key row.group
list_of_predictions.append(prediction)
return list_of_predictions
它适用于本 state_model.predict(data.sample(5))
但打破了，当我尝试这样做： state_model.predict(pd.DataFrame([{'STATE': 'AS'}]))
我的模型无法处理的可能性，我想寻求帮助整顿了。
