Gender Classifier Generator using Tpot

gender_classifier_generator.py

import time
import numpy as np
import sklearn.metrics
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn import svm

from tpot import TPOTClassifier

def name_count(name):
    arr = np.zeros(52 + 26 * 26)
    # iterate each character
    name = name.decode("utf-8")
    for ind, x in enumerate(name):
        try:
            arr[ord(x) - ord('a')] += 1
            arr[ord(x) - ord('a') + 26] += ind + 1
        except TypeError:
            raise TypeError("bytearray from numpy on iteration ")
    # Iterate every 2 character
    for x in range(len(name) - 1):
        try:
            ind = (ord(name[x]) - ord('a')) * 26 - (
                ord(name[x + 1]) - ord('a')) + 52
            arr[ind] += 1
        except TypeError:
            raise TypeError("bytearray from numpy on iteration ")  #

    arr[-3] = ord(name[-1]) - ord('a') + 1

    arr[-2] = ord(name[-2]) - ord('a') + 1
    arr[-1] = len(name)
    return arr

if __name__ == '__main__':
    # data => https://www.ssa.gov/oact/babynames/names.zip
    # TODO: read all the data from the names
    my_data = np.genfromtxt(
        "data/yob2014.txt",
        delimiter=",",
        dtype=[('name', "S50"), ('gender', 'S1'), ('count', 'i4')],
        converters={0: lambda s: s.lower()})

    my_data = np.array([row for row in my_data if row[2] > 20])
    name_map = np.vectorize(name_count, otypes=[np.ndarray])

    Xlist = name_map(my_data['name'].view("S50"))
    X = np.array(Xlist.tolist())
    y = my_data['gender']

    tpot = TPOTClassifier(verbosity=3,
                          scoring="balanced_accuracy",
                          random_state=23,
                          periodic_checkpoint_folder="classifiers_",
                          n_jobs=-1,
                          generations=10,
                          population_size=100)

    X_train, X_test, y_train, y_test =  train_test_split(X, y, test_size=0.33)

    start_time = time.time()
    
    tpot.fit(X_train, y_train)
    
    elapsed = time.time() - start_time
    
    times.append(elapsed)
    
    winning_pipes.append(tpot.fitted_pipeline_)
    scores.append(tpot.score(X_test, y_test))
    
    tpot.export('tpot_pipeline.py')
    times = [time/60 for time in times]
    
    print('Times:', times)
    print('Scores:', scores)
    print('Winning pipelines:', winning_pipes)

run_file.sh

wget --header="Host: www.ssa.gov" --header="User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36" --header="Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3" --header="Accept-Language: en-GB,en-US;q=0.9,en;q=0.8,ml;q=0.7" "https://www.ssa.gov/oact/babynames/names.zip" -O "names.zip" -c


unzip names.zip
mkdir data/

mv *.txt data/

rm -rf rm NationalReadMe.pdf

pip install numpy tpot scikit-learn xgboost tpot

python main.py