Using Text Data with EvalML

In this demo, we will show you how to use EvalML to build models which use text data.

import evalml
from evalml import AutoMLSearch

Dataset

We will be utilizing a dataset of SMS text messages, some of which are categorized as spam, and others which are not (“ham”). This dataset is originally from Kaggle, but modified to produce a slightly more even distribution of spam to ham.

from urllib.request import urlopen
import pandas as pd

input_data = urlopen('https://featurelabs-static.s3.amazonaws.com/spam_text_messages_modified.csv')
data = pd.read_csv(input_data)

X = data.drop(['Category'], axis=1)
y = data['Category']

display(X.head())

	Message
0	Free entry in 2 a wkly comp to win FA Cup fina...
1	FreeMsg Hey there darling it's been 3 week's n...
2	WINNER!! As a valued network customer you have...
3	Had your mobile 11 months or more? U R entitle...
4	SIX chances to win CASH! From 100 to 20,000 po...

The ham vs spam distribution of the data is 3:1, so any machine learning model must get above 75% accuracy in order to perform better than a trivial baseline model which simply classifies everything as ham.

y.value_counts(normalize=True)

ham     0.750084
spam    0.249916
Name: Category, dtype: float64

Search for best pipeline

In order to validate the results of the pipeline creation and optimization process, we will save some of our data as a holdout set.

X_train, X_holdout, y_train, y_holdout = evalml.preprocessing.split_data(X, y, problem_type='binary', test_size=0.2, random_seed=0)

EvalML uses Woodwork to automatically detect which columns are text columns, so you can run search normally, as you would if there was no text data. We can print out the logical type of the Message column and assert that it is indeed inferred as a natural language column.

X_train.ww

	Physical Type	Logical Type	Semantic Tag(s)
Column
Message	string	NaturalLanguage	[]

Because the spam/ham labels are binary, we will use AutoMLSearch(X_train=X_train, y_train=y_train, problem_type='binary'). When we call .search(), the search for the best pipeline will begin.

automl = AutoMLSearch(X_train=X_train, y_train=y_train,
                      problem_type='binary',
                      max_batches=1,
                      optimize_thresholds=True)

automl.search()

Generating pipelines to search over...
8 pipelines ready for search.

*****************************
* Beginning pipeline search *
*****************************

Optimizing for Log Loss Binary.
Lower score is better.

Using SequentialEngine to train and score pipelines.
Searching up to 1 batches for a total of 9 pipelines.
Allowed model families: xgboost, lightgbm, random_forest, linear_model, extra_trees, decision_tree, catboost

Evaluating Baseline Pipeline: Mode Baseline Binary Classification Pipeline
Mode Baseline Binary Classification Pipeline:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 8.638

*****************************
* Evaluating Batch Number 1 *
*****************************

Elastic Net Classifier w/ Text Featurization Component + Standard Scaler:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.222
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        Elastic Net Classifier w/ Text Featurization Component + Standard Scaler may not perform as estimated on unseen data.
Decision Tree Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 1.403
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        Decision Tree Classifier w/ Text Featurization Component may not perform as estimated on unseen data.
Random Forest Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.153
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        Random Forest Classifier w/ Text Featurization Component may not perform as estimated on unseen data.
LightGBM Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.213
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        LightGBM Classifier w/ Text Featurization Component may not perform as estimated on unseen data.
Logistic Regression Classifier w/ Text Featurization Component + Standard Scaler:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.222
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        Logistic Regression Classifier w/ Text Featurization Component + Standard Scaler may not perform as estimated on unseen data.
XGBoost Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.172
        High coefficient of variation (cv >= 0.2) within cross validation scores.
        XGBoost Classifier w/ Text Featurization Component may not perform as estimated on unseen data.
Extra Trees Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.256
CatBoost Classifier w/ Text Featurization Component:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.534

Search finished after 01:00
Best pipeline: Random Forest Classifier w/ Text Featurization Component
Best pipeline Log Loss Binary: 0.152939

View rankings and select pipeline

Once the fitting process is done, we can see all of the pipelines that were searched.

automl.rankings

	id	pipeline_name	search_order	mean_cv_score	standard_deviation_cv_score	validation_score	percent_better_than_baseline	high_variance_cv	parameters
0	3	Random Forest Classifier w/ Text Featurization...	3	0.152939	0.043389	0.113306	98.229529	True	{'Random Forest Classifier': {'n_estimators': ...
1	6	XGBoost Classifier w/ Text Featurization Compo...	6	0.171712	0.046956	0.120741	98.012206	True	{'XGBoost Classifier': {'eta': 0.1, 'max_depth...
2	4	LightGBM Classifier w/ Text Featurization Comp...	4	0.212777	0.056598	0.147567	97.536822	True	{'LightGBM Classifier': {'boosting_type': 'gbd...
3	1	Elastic Net Classifier w/ Text Featurization C...	1	0.221790	0.045718	0.172468	97.432481	True	{'Elastic Net Classifier': {'penalty': 'elasti...
4	5	Logistic Regression Classifier w/ Text Featuri...	5	0.221831	0.045594	0.172700	97.432008	True	{'Logistic Regression Classifier': {'penalty':...
5	7	Extra Trees Classifier w/ Text Featurization C...	7	0.255506	0.050486	0.224186	97.042171	False	{'Extra Trees Classifier': {'n_estimators': 10...
6	8	CatBoost Classifier w/ Text Featurization Comp...	8	0.533608	0.014352	0.523532	93.822767	False	{'CatBoost Classifier': {'n_estimators': 10, '...
7	2	Decision Tree Classifier w/ Text Featurization...	2	1.403436	0.553454	0.775794	83.753347	True	{'Decision Tree Classifier': {'criterion': 'gi...
8	0	Mode Baseline Binary Classification Pipeline	0	8.638305	0.025020	8.623860	0.000000	False	{'Baseline Classifier': {'strategy': 'mode'}}

To select the best pipeline we can call automl.best_pipeline.

best_pipeline = automl.best_pipeline

Describe pipeline

You can get more details about any pipeline, including how it performed on other objective functions.

automl.describe_pipeline(automl.rankings.iloc[0]["id"])

************************************************************
* Random Forest Classifier w/ Text Featurization Component *
************************************************************

Problem Type: binary
Model Family: Random Forest

Pipeline Steps
==============
1. Text Featurization Component
2. Random Forest Classifier
         * n_estimators : 100
         * max_depth : 6
         * n_jobs : -1

Training
========
Training for binary problems.
Total training time (including CV): 7.6 seconds

Cross Validation
----------------
             Log Loss Binary  MCC Binary   AUC  Precision    F1  Balanced Accuracy Binary  Accuracy Binary # Training # Validation
0                      0.113       0.899 0.987      0.896 0.925                     0.959            0.961      1,594          797
1                      0.146       0.838 0.978      0.887 0.878                     0.916            0.940      1,594          797
2                      0.199       0.789 0.968      0.848 0.841                     0.892            0.921      1,594          797
mean                   0.153       0.842 0.978      0.877 0.881                     0.923            0.941          -            -
std                    0.043       0.055 0.009      0.026 0.042                     0.034            0.020          -            -
coef of var            0.284       0.066 0.010      0.029 0.047                     0.037            0.021          -            -

best_pipeline.graph()

Notice above that there is a Text Featurization Component as the first step in the pipeline. The Woodwork DataTable passed in to AutoML search recognizes that 'Message' is a text column, and converts this text into numerical values that can be handled by the estimator.

Evaluate on holdout

Now, we can score the pipeline on the holdout data using the core objectives for binary classification problems.

scores = best_pipeline.score(X_holdout, y_holdout,  objectives=evalml.objectives.get_core_objectives('binary'))
print(f'Accuracy Binary: {scores["Accuracy Binary"]}')

Accuracy Binary: 0.9715719063545151

As you can see, this model performs relatively well on this dataset, even on unseen data.

Why encode text this way?

To demonstrate the importance of text-specific modeling, let’s train a model with the same dataset, without letting AutoMLSearch detect the text column. We can change this by explicitly setting the data type of the 'Message' column in Woodwork to Categorical using the utility method infer_feature_types.

from evalml.utils import infer_feature_types
X = infer_feature_types(X, {'Message': 'Categorical'})
X_train, X_holdout, y_train, y_holdout = evalml.preprocessing.split_data(X, y, problem_type='binary', test_size=0.2, random_seed=0)

automl_no_text = AutoMLSearch(X_train=X_train, y_train=y_train,
                              problem_type='binary',
                              max_batches=1,
                              optimize_thresholds=True)

automl_no_text.search()

Generating pipelines to search over...
8 pipelines ready for search.

*****************************
* Beginning pipeline search *
*****************************

Optimizing for Log Loss Binary.
Lower score is better.

Using SequentialEngine to train and score pipelines.
Searching up to 1 batches for a total of 9 pipelines.
Allowed model families: xgboost, lightgbm, random_forest, linear_model, extra_trees, decision_tree, catboost

Evaluating Baseline Pipeline: Mode Baseline Binary Classification Pipeline
Mode Baseline Binary Classification Pipeline:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 8.638

*****************************
* Evaluating Batch Number 1 *
*****************************

Elastic Net Classifier w/ Imputer + One Hot Encoder + Standard Scaler:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.561
Decision Tree Classifier w/ Imputer + One Hot Encoder:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.561
Random Forest Classifier w/ Imputer + One Hot Encoder:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.561
LightGBM Classifier w/ Imputer + One Hot Encoder:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.562
Logistic Regression Classifier w/ Imputer + One Hot Encoder + Standard Scaler:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.561
XGBoost Classifier w/ Imputer + One Hot Encoder:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.562
Extra Trees Classifier w/ Imputer + One Hot Encoder:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.561
CatBoost Classifier w/ Imputer:
        Starting cross validation
        Finished cross validation - mean Log Loss Binary: 0.631

Search finished after 00:06
Best pipeline: Logistic Regression Classifier w/ Imputer + One Hot Encoder + Standard Scaler
Best pipeline Log Loss Binary: 0.560995

Like before, we can look at the rankings and pick the best pipeline.

automl_no_text.rankings

	id	pipeline_name	search_order	mean_cv_score	standard_deviation_cv_score	validation_score	percent_better_than_baseline	high_variance_cv	parameters
0	5	Logistic Regression Classifier w/ Imputer + On...	5	0.560995	0.001805	0.560347	93.505723	False	{'Imputer': {'categorical_impute_strategy': 'm...
1	1	Elastic Net Classifier w/ Imputer + One Hot En...	1	0.561000	0.001804	0.560350	93.505674	False	{'Imputer': {'categorical_impute_strategy': 'm...
2	2	Decision Tree Classifier w/ Imputer + One Hot ...	2	0.561199	0.002170	0.560353	93.503373	False	{'Imputer': {'categorical_impute_strategy': 'm...
3	3	Random Forest Classifier w/ Imputer + One Hot ...	3	0.561386	0.001712	0.560692	93.501207	False	{'Imputer': {'categorical_impute_strategy': 'm...
4	7	Extra Trees Classifier w/ Imputer + One Hot En...	7	0.561418	0.001676	0.560625	93.500837	False	{'Imputer': {'categorical_impute_strategy': 'm...
5	6	XGBoost Classifier w/ Imputer + One Hot Encoder	6	0.562262	0.000769	0.561991	93.491057	False	{'Imputer': {'categorical_impute_strategy': 'm...
6	4	LightGBM Classifier w/ Imputer + One Hot Encoder	4	0.562452	0.000798	0.561991	93.488867	False	{'Imputer': {'categorical_impute_strategy': 'm...
7	8	CatBoost Classifier w/ Imputer	8	0.631214	0.004016	0.633875	92.692846	False	{'Imputer': {'categorical_impute_strategy': 'm...
8	0	Mode Baseline Binary Classification Pipeline	0	8.638305	0.025020	8.623860	0.000000	False	{'Baseline Classifier': {'strategy': 'mode'}}

best_pipeline_no_text = automl_no_text.best_pipeline

Here, changing the data type of the text column removed the Text Featurization Component from the pipeline.

best_pipeline_no_text.graph()

automl_no_text.describe_pipeline(automl_no_text.rankings.iloc[0]["id"])

*********************************************************************************
* Logistic Regression Classifier w/ Imputer + One Hot Encoder + Standard Scaler *
*********************************************************************************

Problem Type: binary
Model Family: Linear

Pipeline Steps
==============
1. Imputer
         * categorical_impute_strategy : most_frequent
         * numeric_impute_strategy : mean
         * categorical_fill_value : None
         * numeric_fill_value : None
2. One Hot Encoder
         * top_n : 10
         * features_to_encode : None
         * categories : None
         * drop : if_binary
         * handle_unknown : ignore
         * handle_missing : error
3. Standard Scaler
4. Logistic Regression Classifier
         * penalty : l2
         * C : 1.0
         * n_jobs : -1
         * multi_class : auto
         * solver : lbfgs

Training
========
Training for binary problems.
Total training time (including CV): 0.6 seconds

Cross Validation
----------------
             Log Loss Binary  MCC Binary   AUC  Precision    F1  Balanced Accuracy Binary  Accuracy Binary # Training # Validation
0                      0.560       0.000 0.503      0.000 0.000                     0.500            0.750      1,594          797
1                      0.560       0.000 0.504      0.000 0.000                     0.500            0.750      1,594          797
2                      0.563       0.000 0.502      0.000 0.000                     0.500            0.749      1,594          797
mean                   0.561       0.000 0.503      0.000 0.000                     0.500            0.750          -            -
std                    0.002       0.000 0.001      0.000 0.000                     0.000            0.001          -            -
coef of var            0.003         inf 0.003        inf   inf                     0.000            0.001          -            -

# get standard performance metrics on holdout data
scores = best_pipeline_no_text.score(X_holdout, y_holdout, objectives=evalml.objectives.get_core_objectives('binary'))
print(f'Accuracy Binary: {scores["Accuracy Binary"]}')

Accuracy Binary: 0.7508361204013378

Without the Text Featurization Component, the 'Message' column was treated as a categorical column, and therefore the conversion of this text to numerical features happened in the One Hot Encoder. The best pipeline encoded the top 10 most frequent “categories” of these texts, meaning 10 text messages were one-hot encoded and all the others were dropped. Clearly, this removed almost all of the information from the dataset, as we can see the best_pipeline_no_text performs very similarly to randomly guessing “ham” in every case.

Using the Cost-Benefit Matrix Objective User Guide