如何采取用户输入并传递到预测模型

Question

我有我建立了一个预测模型中的数据帧。所述数据被划分到训练和测试，并且我已经使用随机森林分类器。

现在，用户通过新的数据，这需要通过这个模型，给出了结果。

这是一个文本数据，以下是数据框：

     Description          Category
     Rejoin this domain   Network
     Laptop crashed       Hardware
     Installation Error   Software

代码：

  ############### Feature extraction ##############
  countvec = CountVectorizer()
  counts = countvec.fit_transform(read_data['Description'])
  df = pd.DataFrame(counts.toarray())
  df.columns = countvec.get_feature_names()
  print(df)

  ########## Join with original data ##############
  df = read_data.join(df)
  a = list(df.columns.values)

  ########## Creating the dependent variable class for "Category" variable 
  ###########
  factor = pd.factorize(df['Category'])
  df.Category = factor[0]
  definitions = factor[1]
  print(df.Category.head())
  print(definitions)

  ########## Creating the dependent variable class for "Description" 
  variable ###########
  factor = pd.factorize(df['Description'])
  df.Description = factor[0]
  definitions_1 = factor[1]
  print(df.Description.head())
  print(definitions_1)

  ######### Split into Train and Test data #######################
  X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.80, random_state = 21)

  ############# Random forest classification model #########################
  classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 42)
  classifier.fit(X_train, y_train)

  ######### Predicting the Test set results ##############
  y_pred = classifier.predict(X_test)

  #####Reverse factorize (converting y_pred from 0s,1s and 2s to original class for "Category" ###############
  reversefactor = dict(zip(range(3),definitions))
  y_test = np.vectorize(reversefactor.get)(y_test)
  y_pred = np.vectorize(reversefactor.get)(y_pred)

  #####Reverse factorize (converting y_pred from 0s,1s and 2s to original class for "Description" ###############
  reversefactor = dict(zip(range(53),definitions_1))
  X_test = np.vectorize(reversefactor.get)(X_test)

Answer 1

如果你只想做对用户的数据预测，那么我会简单地装载包含用户数据的新CSV（或其他格式）（确保列是一样的，在原来的训练数据集，减去因变量明显）你可以拉你的任务的预测：

user_df = pd.read_csv("user_data.csv")

#insert a preprocessing step if needed to make sure user_df is identical to the original dataset

new_predictions = classifier.predict(user_df)