我最终想出了这个办法,尽管和上面的有点不同。。。
# Set Data Location:
data = 'top10000.csv'
# load the data
df = pd.read_csv(data,low_memory=False,thousands=',', encoding='latin-1')
df = df.dropna()
df = df[['CODE','DUTIES']] #select only these columns
#df = df.rename(index=float, columns={"CODE": "label", "DUTIES": "text"})
df = df.rename(columns={"CODE": "label", "DUTIES": "text"})
#Convert label to float so you don't need to encode for processing later on
df['label']=df['label'].str.replace('-', '',regex=True, case = False).str.strip()
df['label']=df['label'].str.replace('.', '',regex=True)
#df['label']=pd.to_numeric(df['label'])
df['label']=df['label'].str[1:].astype(int)
#df['label'].astype('float64', raise_on_error = True)
#split data into testing and training
train_x, valid_x, train_y, valid_y = model_selection.train_test_split(df.text, df.label,test_size=0.33, random_state=6)
#reset the index
valid_y = valid_y.reset_index(drop=True)
valid_x = valid_x.reset_index(drop=True)
# We will also copy the validation datasets to a dataframe to be able to merge later on
valid_x_df = pd.DataFrame(valid_x)
valid_y_df = pd.DataFrame(valid_y)
# Extracte features
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(train_x)
X_test_counts = count_vect.transform(valid_x)
# Define the model training and validation function
def TV_model(classifier, feature_vector_train, label, feature_vector_valid, valid_y, valid_x, is_neural_net=False):
# fit the training dataset on the classifier
classifier.fit(feature_vector_train, label)
# predict the top n labels on validation dataset
n = 5
#classifier.probability = True
probas = classifier.predict_proba(feature_vector_valid)
predictions = classifier.predict(feature_vector_valid)
#Identify the indexes of the top predictions
top_n_predictions = np.argsort(probas, axis = 1)[:,-n:]
#then find the associated SOC code for each prediction
top_class = classifier.classes_[top_n_predictions]
#cast to a new dataframe
top_class_df = pd.DataFrame(data=top_class)
#merge it up with the validation labels and descriptions
results = pd.merge(valid_y, valid_x, left_index=True, right_index=True)
results = pd.merge(results, top_class_df, left_index=True, right_index=True)
# Top 5 results condiions and choices
top5_conditions = [
(results.iloc[:,0] == results[0]),
(results.iloc[:,0] == results[1]),
(results.iloc[:,0] == results[2]),
(results.iloc[:,0] == results[3]),
(results.iloc[:,0] == results[4])]
top5_choices = [1, 1, 1, 1, 1]
# Fetch Top 1 Result
top1_conditions = [(results.iloc[:,0] == results[4])]
top1_choices = [1]
# Create the success columns
results['Top 5 Successes'] = np.select(top5_conditions, top5_choices, default=0)
results['Top 1 Successes'] = np.select(top1_conditions, top1_choices, default=0)
#Print the QA
print("Are Top 5 Results greater than Top 1 Result? (answer must be True): ", (sum(results['Top 5 Successes'])/results.shape[0])>(metrics.accuracy_score(valid_y, predictions)))
print("Are Top 1 Results equal from predict() and predict_proba()? (answer must be True): ", (sum(results['Top 1 Successes'])/results.shape[0])==(metrics.accuracy_score(valid_y, predictions)))
print(" ")
print("Details: ")
print("Top 5 Accuracy Rate (predict_proba)= ", sum(results['Top 5 Successes'])/results.shape[0])
#print("Top 5 Accuracy Rate (np.mean)= ", np.mean(np.array([1 if valid_y[k] in top_class[k] else 0 for k in range(len(top_class))])))
print("Top 1 Accuracy Rate (predict_proba)= ", sum(results['Top 1 Successes'])/results.shape[0])
print("Top 1 Accuracy Rate = (predict)", metrics.accuracy_score(valid_y, predictions))
# Train and validate model from example data using the function defined above
TV_model(LogisticRegression(), X_train_counts, train_y, X_test_counts, valid_y_df, valid_x_df)
我相信这可能是更有效的计算,所以任何建议,我可以转换成一个线性的准确率计算,如在上面的意见建议将不胜感激!