example.py

# Author: Peter Prettenhofer <peter.prettenhofer@gmail.com>
#         Olivier Grisel <olivier.grisel@ensta.org>
#         Mathieu Blondel <mathieu@mblondel.org>
#         Lars Buitinck
# License: BSD 3 clause

from __future__ import print_function

import re
import logging
import numpy as np
from optparse import OptionParser
import sys
from time import time
import matplotlib.pyplot as plt

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_selection import SelectFromModel
from sklearn.feature_selection import SelectKBest, chi2
from sklearn.linear_model import RidgeClassifier
from sklearn.pipeline import Pipeline
from sklearn.svm import LinearSVC
from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import Perceptron
from sklearn.linear_model import PassiveAggressiveClassifier
from sklearn.naive_bayes import BernoulliNB, ComplementNB, MultinomialNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import NearestCentroid
from sklearn.ensemble import RandomForestClassifier
from sklearn.utils.extmath import density
from sklearn import metrics


# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
                    format='%(asctime)s %(levelname)s %(message)s')


# parse commandline arguments
op = OptionParser()
op.add_option("--report",
              action="store_true", dest="print_report",
              help="Print a detailed classification report.")
op.add_option("--chi2_select",
              action="store", type="int", dest="select_chi2",
              help="Select some number of features using a chi-squared test")
op.add_option("--confusion_matrix",
              action="store_true", dest="print_cm",
              help="Print the confusion matrix.")
op.add_option("--top10",
              action="store_true", dest="print_top10",
              help="Print ten most discriminative terms per class"
                   " for every classifier.")
op.add_option("--all_categories",
              action="store_true", dest="all_categories",
              help="Whether to use all categories or not.")
op.add_option("--use_hashing",
              action="store_true",
              help="Use a hashing vectorizer.")
op.add_option("--n_features",
              action="store", type=int, default=2 ** 16,
              help="n_features when using the hashing vectorizer.")
op.add_option("--filtered",
              action="store_true",
              help="Remove newsgroup information that is easily overfit: "
                   "headers, signatures, and quoting.")


def is_interactive():
    return not hasattr(sys.modules['__main__'], '__file__')


# work-around for Jupyter notebook and IPython console
argv = [] if is_interactive() else sys.argv[1:]
(opts, args) = op.parse_args(argv)
if len(args) > 0:
    op.error("this script takes no arguments.")
    sys.exit(1)

print(__doc__)
op.print_help()
print()


import psycopg2
from sklearn.model_selection import train_test_split

conn = psycopg2.connect("dbname=postgres user=postgres host=127.0.0.1")
cur = conn.cursor()
# cur.execute("SELECT description, hcpcs_code FROM charge_master_lines WHERE description IS NOT NULL and hcpcs_code LIKE '1____';")
cur.execute("SELECT description, hcpcs_code FROM charge_master_lines WHERE hcpcs_code IN (SELECT hcpcs_code FROM charge_master_lines WHERE description IS NOT NULL and hcpcs_code LIKE '1____' GROUP BY hcpcs_code HAVING COUNT(description) >= 5);")

X = list()
y = list()

canonical_phrases = {
    'FINE NEEDLE ASPIRATION': 'FNA',
    'FINE NEEDLE': 'FNE NDL',
    'WITHOUT GUIDANCE': 'WO GUIDE',
    'WITH GUIDANCE': 'W GUIDE',
    'IMAGING GUIDANCE': 'IMAGINE GUID',
    'NEEDLE ASPIRATION': 'NDL ASPIR',
    'NEEDLE ASPIRATION': 'NEEDLE ASP',
    'NEEDLE': 'NDL',
    'NEEDLE': 'NDLE',

    'WITHOUT': 'W/O',
    'WITHOUT': 'WO',
    'WITHOUT': 'W\\O',
    'WITHOUT': 'W/OUT',

    'WITH': 'W/',
    'WITH': 'W\\',
    'WITH': 'W',

    'IMAGE': 'IMAG\\',
    'IMAGE': 'IMAG\\',
    'IMAGE': 'IMG\\',

    'CATHETER': 'CATHET\\',
    'CATHETER': 'CATH\\',
    'SOFT TISSUE': 'SFT TISS\\',
    'COLLECTION': 'COLL\\',

    'SURGERY': 'SUGE',
    'CYSTS': 'SYSTS',

    'INCISION DRAINAGE': 'I+D',
    'INCISION DRAINAGE': 'I/D',
    'INCISION DRAINAGE': 'I & D',
    'INCISION DRAINAGE': 'INCISION & DRAINAGE',
    'INCISION DRAINAGE': 'I D',

    'FLUID COLLECTION': 'FLD COLL',
    'ABSCESS': 'ABSC',
    'ABSCESS': 'ABCESS',
    'SUBCUTANEOUS': 'SUBCUT',
    'SUBCUTANEOUS': 'SQ',
    'SUBCUTANEOUS': 'SUBQ',

    'SIMPLE OR SINGLE': 'SMPL OR SGL',
    'SIMPLE OR SINGLE': 'SIMPL/SNGL',
    'SIMPLE OR SINGLE': 'SIMPLE/SINGLE',
    'SIMPLE OR SINGLE': 'SIMPLE OR SINGLE',
    'SIMPLE OR SINGLE': 'SIMPLE OR SINGL',

    'COMPLEX OR MULTIPLE': 'COMPL OR MULTI',
    'COMPLEX OR MULTIPLE': 'COMPLIC/MX',
    'COMPLEX OR MULTIPLE': 'COMPLX OR MULTI',
    'COMPLEX OR MULTIPLE': 'COMPLEX/MULTI',
    'COMPLEX OR MULTIPLE': 'COMP/MULT',
    'COMPLEX OR MULTIPLE': 'CMPX/MULT',

    'COMPLEX': 'COMPLICATED',
    'COMPLEX': 'CPLX',
    'MULTIPLE': 'MULT',

    'DEBRIDE': 'DEBRID',
    'DEBRIDE': 'DEBRIDEMENT',

    'BIOPSY': 'BX',
    'BODY': 'BDY',
    'FOREIGN BODY': 'FB',
    'SIMPLE': 'SMPL',
}

canonical_phrase_compiled = []

for k, v in canonical_phrases.items():
    canonical_phrase_compiled.append(
        { 'r': k, 'p': re.compile(r"\b" + re.escape(v) + "\b", flags=re.IGNORECASE) })

def canonicalize_phrase(description):
    for item in canonical_phrase_compiled:
        description = re.sub(item['p'], item['r'], description)

    return description

for record in cur:
    X.append(canonicalize_phrase(record[0]))

    if len(record[1]) == 5 and record[1].startswith('1'):
        y.append(record[1])
    else:
        y.append(None)

def size_mb(docs):
    return sum(len(s.encode('utf-8')) for s in docs) / 1e6

Xtrain, Xtest, ytrain, ytest = train_test_split(
    X, y, test_size=0.33, random_state=42)

data_train_size_mb = size_mb(Xtrain)
data_test_size_mb = size_mb(Xtest)
target_names = set(y)

print("%d documents - %0.3fMB (training set)" % (
    len(Xtrain), data_train_size_mb))
print("%d documents - %0.3fMB (test set)" % (
    len(Xtest), data_test_size_mb))
print("%d categories" % len(target_names))
print()

print("Extracting features from the training data using a sparse vectorizer")
t0 = time()
if opts.use_hashing:
    vectorizer = HashingVectorizer(stop_words='english', alternate_sign=False,
                                   n_features=opts.n_features)
    X_train = vectorizer.transform(Xtrain)
else:
    vectorizer = TfidfVectorizer(
        sublinear_tf=True,
        # max_df=0.5,
        token_pattern=r"(?u)\b[-&\w][-&\w]+\b",
        # ngram_range=[1, 3],
        stop_words=None)

    X_train = vectorizer.fit_transform(Xtrain)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, data_train_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_train.shape)
print()

print("Extracting features from the test data using the same vectorizer")
t0 = time()
X_test = vectorizer.transform(Xtest)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, data_test_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_test.shape)
print()

# mapping from integer feature name to original token string
if opts.use_hashing:
    feature_names = None
else:
    feature_names = vectorizer.get_feature_names()
    print(sorted(feature_names))

if opts.select_chi2:
    print("Extracting %d best features by a chi-squared test" %
          opts.select_chi2)
    t0 = time()
    ch2 = SelectKBest(chi2, k=opts.select_chi2)
    X_train = ch2.fit_transform(X_train, ytrain)
    X_test = ch2.transform(X_test)
    if feature_names:
        # keep selected feature names
        feature_names = [feature_names[i] for i
                         in ch2.get_support(indices=True)]
    print("done in %fs" % (time() - t0))
    print()

if feature_names:
    feature_names = np.asarray(feature_names)


def trim(s):
    """Trim string to fit on terminal (assuming 80-column display)"""
    return s if len(s) <= 80 else s[:77] + "..."


# #############################################################################
# Benchmark classifiers
def benchmark(clf):
    print('_' * 80)
    print("Training: ")
    print(clf)
    t0 = time()
    clf.fit(X_train, ytrain)
    train_time = time() - t0
    print("train time: %0.3fs" % train_time)

    t0 = time()
    pred = clf.predict(X_test)
    test_time = time() - t0
    print("test time:  %0.3fs" % test_time)

    score = metrics.accuracy_score(ytest, pred)
    print("accuracy:   %0.3f" % score)

    if hasattr(clf, 'coef_'):
        print("dimensionality: %d" % clf.coef_.shape[1])
        print("density: %f" % density(clf.coef_))

        if opts.print_top10 and feature_names is not None:
            print("top 10 keywords per class:")
            for i, label in enumerate(target_names):
                top10 = np.argsort(clf.coef_[i])[-10:]
                print(trim("%s: %s" % (label, " ".join(feature_names[top10]))))
        print()

    if opts.print_report:
        print("classification report:")
        print(metrics.classification_report(ytest, pred,
                                            target_names=target_names))

    if opts.print_cm:
        print("confusion matrix:")
        print(metrics.confusion_matrix(ytest, pred))

    print()
    clf_descr = str(clf).split('(')[0]
    return clf_descr, score, train_time, test_time


results = []
for clf, name in (
        (RidgeClassifier(tol=1e-2, solver="sag"), "Ridge Classifier"),
        (Perceptron(max_iter=50, tol=1e-3), "Perceptron"),
        (PassiveAggressiveClassifier(max_iter=50, tol=1e-3),
         "Passive-Aggressive"),
        (KNeighborsClassifier(n_neighbors=10), "kNN"),
        (RandomForestClassifier(n_estimators=100), "Random forest")):
    print('=' * 80)
    print(name)
    results.append(benchmark(clf))

for penalty in ["l2", "l1"]:
    print('=' * 80)
    print("%s penalty" % penalty.upper())
    # Train Liblinear model
    results.append(benchmark(LinearSVC(penalty=penalty, dual=False,
                                       tol=1e-3)))

    # Train SGD model
    results.append(benchmark(SGDClassifier(alpha=.0001, max_iter=50,
                                           penalty=penalty)))

# Train SGD with Elastic Net penalty
print('=' * 80)
print("Elastic-Net penalty")
results.append(benchmark(SGDClassifier(alpha=.0001, max_iter=50,
                                       penalty="elasticnet")))

# Train NearestCentroid without threshold
print('=' * 80)
print("NearestCentroid (aka Rocchio classifier)")
results.append(benchmark(NearestCentroid()))

# Train sparse Naive Bayes classifiers
print('=' * 80)
print("Naive Bayes")
results.append(benchmark(MultinomialNB(alpha=.01)))
results.append(benchmark(BernoulliNB(alpha=.01)))
results.append(benchmark(ComplementNB(alpha=.1)))

print('=' * 80)
print("LinearSVC with L1-based feature selection")
# The smaller C, the stronger the regularization.
# The more regularization, the more sparsity.
results.append(benchmark(Pipeline([
  ('feature_selection', SelectFromModel(LinearSVC(penalty="l1", dual=False,
                                                  tol=1e-3))),
  ('classification', LinearSVC(penalty="l2"))])))

# make some plots

indices = np.arange(len(results))

results = [[x[i] for x in results] for i in range(4)]

clf_names, score, training_time, test_time = results
training_time = np.array(training_time) / np.max(training_time)
test_time = np.array(test_time) / np.max(test_time)

plt.figure(figsize=(12, 8))
plt.title("Score")
plt.barh(indices, score, .2, label="score", color='navy')
plt.barh(indices + .3, training_time, .2, label="training time",
         color='c')
plt.barh(indices + .6, test_time, .2, label="test time", color='darkorange')
plt.yticks(())
plt.legend(loc='best')
plt.subplots_adjust(left=.25)
plt.subplots_adjust(top=.95)
plt.subplots_adjust(bottom=.05)

for i, c in zip(indices, clf_names):
    plt.text(-.3, i, c)

plt.show()