python - pickle 序列化: module '__main__' has no attribute 'tokenize'

Question

我有一个训练机器学习模型并通过 pickle 保存它的脚本:

当我尝试将模型加载到网站时，我收到错误消息:“模块‘ma​​in’没有属性‘tokenize’”。我尝试导入函数“tokenize”并直接将其复制到加载脚本中，但没有任何效果

完整的训练脚本:

import sys
import pandas as pd
import numpy as np
from sqlalchemy import create_engine
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
import re
import seaborn as sns
from nltk.stem.wordnet import WordNetLemmatizer
from nltk.stem.porter import PorterStemmer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.multioutput import MultiOutputClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, fbeta_score, make_scorer
from sklearn.model_selection import GridSearchCV
from sklearn.externals import joblib

import pickle

nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')


def load_data(database_filepath):
    """takes path to db as input and loads data. Return X, Y and target_names"""
    engine = create_engine('sqlite:///{}'.format(database_filepath))
    df = pd.read_sql('disaster_data', engine)
    X = df.message.values
    Y = df.drop(['message', 'id', 'original', 'genre'], axis=1).values
    target_names = df.drop(['message', 'id', 'original', 'genre'], axis=1).columns

    return X, Y, target_names

def tokenize(text):
    """Takes a text as input an returns a list of tokenized words"""
    stop_words = stopwords.words("english")
    text = re.sub(r"[^a-zA-Z0-9]", " ", text).lower().strip()
    words = word_tokenize(text)
    clean_words = [w for w in words if w not in stopwords.words("english")]
    tokens = [WordNetLemmatizer().lemmatize(w) for w in words if w not in stop_words]
    clean_tokens = [PorterStemmer().stem(w) for w in tokens]

    return clean_tokens

def build_model():
    """Builds a model. returns a GridSearchCV object"""
    pipeline = Pipeline([
        ('vect', CountVectorizer(tokenizer=tokenize)),
        ('tfidf', TfidfTransformer()),
        ('clf', MultiOutputClassifier(RandomForestClassifier(), n_jobs=1)),
        ])
    parameters = {'clf__estimator__max_depth': [30],
                  'clf__estimator__min_samples_leaf': [5],
                  'clf__estimator__min_samples_split': [5],
                  'clf__estimator__n_estimators': [100]}



    return GridSearchCV(estimator=pipeline, param_grid=parameters, verbose=10, n_jobs=1)


def evaluate_model(model, X_test, Y_test, category_names):
    """Takes model, X_test, Y_test and category names as input and evaluates model"""
    y_pred = model.predict(X_test)
    print("Accuracy of the model :", (y_pred == Y_test).mean())
    for i in y_pred:
        print(classification_report(Y_test, y_pred, target_names=category_names))
        break


def save_model(model, model_filepath):
    """Takes model and path for saving as input and saves the model"""
    pickle.dump(model, open(model_filepath, 'wb'))
    # Uncommetn for joblib saving
    # joblib.dump(model, model_filepath)

def main():
    """Main function"""
    if len(sys.argv) == 3:
        database_filepath, model_filepath = sys.argv[1:]
        print('Loading data...\n    DATABASE: {}'.format(database_filepath))
        X, Y, category_names = load_data(database_filepath)
        X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2)

        print('Building model...')
        model = build_model()

        print('Training model...')
        model.fit(X_train, Y_train)

        print('Evaluating model...')
        evaluate_model(model, X_test, Y_test, category_names)

        print('Saving model...\n    MODEL: {}'.format(model_filepath))
        save_model(model, model_filepath)

        print('Trained model saved!')

    else:
        print('Please provide the filepath of the disaster messages database '\
              'as the first argument and the filepath of the pickle file to '\
              'save the model to as the second argument. \n\nExample: python '\
              'train_classifier.py ../data/DisasterResponse.db classifier.pkl')


if __name__ == '__main__':
    main()

加载脚本:

import json
import plotly
import pandas as pd
import nltk
import pickle
from nltk.stem import WordNetLemmatizer

from flask import Flask
from flask import render_template, request, jsonify
from plotly.graph_objs import Bar
from sklearn.externals import joblib
from sklearn.feature_extraction.text import CountVectorizer
from sqlalchemy import create_engine
from nltk.corpus import stopwords

from flask import render_template
from wrangling_scripts.wrangle_data import return_figures
from nltk.stem.wordnet import WordNetLemmatizer
from nltk.stem.porter import PorterStemmer
from train_classifier_for_web import tokenize


nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')

app = Flask(__name__)


def tokenize(text):
    """Takes a text as input an returns a list of tokenized words"""
    stop_words = stopwords.words("english")
    text = re.sub(r"[^a-zA-Z0-9]", " ", text).lower().strip()
    words = word_tokenize(text)
    clean_words = [w for w in words if w not in stopwords.words("english")]
    tokens = [WordNetLemmatizer().lemmatize(w) for w in words if w not in stop_words]
    return [PorterStemmer().stem(w) for w in tokens]

    return clean_tokens

@app.before_first_request
def main():
    try:
        engine = create_engine('sqlite:///DisasterResponse.db')
        df = pd.read_sql_table('disaster_data', engine)
    except:
        print("path error to sql db")
    try:
        model = joblib.load('web_model.sav','rb')
    except Exception as e:
        print("cant load model", e)

Answer 1

已解决:

我尝试将标记化函数保存在一个单独的模块中，并在训练脚本和加载脚本中以相同的方式导入它