tldr
KggleのZoo Animal ClassificationをTabular Zoo Animal Classification - Data Every Day #032に沿ってやっていきます。
実行環境はGoogle Colaboratorです。
インポート
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import sklearn.preprocessing as sp
from sklearn.model_selection import train_test_split
import tensorflow as tf
データのダウンロード
Google Driveをマウントします。
from google.colab import drive
drive.mount('/content/drive')
Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
KaggleのAPIクライアントを初期化し、認証します。
認証情報はGoogle Drive内（/content/drive/My Drive/Colab Notebooks/Kaggle）にkaggle.jsonとして置いてあります。
import os
kaggle_path = "/content/drive/My Drive/Colab Notebooks/Kaggle"
os.environ['KAGGLE_CONFIG_DIR'] = kaggle_path
from kaggle.api.kaggle_api_extended import KaggleApi
api = KaggleApi()
api.authenticate()
Kaggle APIを使ってデータをダウンロードします。
dataset_id = 'uciml/zoo-animal-classification'
dataset = api.dataset_list_files(dataset_id)
file_name = dataset.files[0].name
file_path = os.path.join(api.get_default_download_dir(), file_name)
file_path
Warning: Looks like you're using an outdated API Version, please consider updating (server 1.5.10 / client 1.5.9)
'/content/zoo.csv'
api.dataset_download_file(dataset_id, file_name, force=True, quiet=False)
100%|██████████| 4.27k/4.27k [00:00<00:00, 1.04MB/s]
Downloading zoo.csv to /content
True
データの読み込み
Padasを使ってダウンロードしてきたCSVファイルを読み込みます。
data = pd.read_csv(file_path)
data
| animal_name | hair | feathers | eggs | milk | airborne | aquatic | predator | toothed | backbone | breathes | venomous | fins | legs | tail | domestic | catsize | class_type | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | aardvark | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 4 | 0 | 0 | 1 | 1 |
| 1 | antelope | 1 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 4 | 1 | 0 | 1 | 1 |
| 2 | bass | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 1 | 0 | 1 | 0 | 0 | 4 |
| 3 | bear | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 4 | 0 | 0 | 1 | 1 |
| 4 | boar | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 4 | 1 | 0 | 1 | 1 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 96 | wallaby | 1 | 0 | 0 | 1 | 0 | 0 | 0 | 1 | 1 | 1 | 0 | 0 | 2 | 1 | 0 | 1 | 1 |
| 97 | wasp | 1 | 0 | 1 | 0 | 1 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 6 | 0 | 0 | 0 | 6 |
| 98 | wolf | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 1 | 1 | 1 | 0 | 0 | 4 | 1 | 0 | 1 | 1 |
| 99 | worm | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 7 |
| 100 | wren | 0 | 1 | 1 | 0 | 1 | 0 | 0 | 0 | 1 | 1 | 0 | 0 | 2 | 1 | 0 | 0 | 2 |
101 rows × 18 columns
下準備
不要な列の削除
data = data.drop('animal_name', axis=1)
data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 101 entries, 0 to 100
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 hair 101 non-null int64
1 feathers 101 non-null int64
2 eggs 101 non-null int64
3 milk 101 non-null int64
4 airborne 101 non-null int64
5 aquatic 101 non-null int64
6 predator 101 non-null int64
7 toothed 101 non-null int64
8 backbone 101 non-null int64
9 breathes 101 non-null int64
10 venomous 101 non-null int64
11 fins 101 non-null int64
12 legs 101 non-null int64
13 tail 101 non-null int64
14 domestic 101 non-null int64
15 catsize 101 non-null int64
16 class_type 101 non-null int64
dtypes: int64(17)
memory usage: 13.5 KB
データはとてもきれいです。ほぼやることがない。
分割とスケーリング
y = data['class_type']
X = data.drop('class_type', axis=1)
scaler = sp.MinMaxScaler()
X = pd.DataFrame(scaler.fit_transform(X), columns=X.columns)
X
| hair | feathers | eggs | milk | airborne | aquatic | predator | toothed | backbone | breathes | venomous | fins | legs | tail | domestic | catsize | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.50 | 0.0 | 0.0 | 1.0 |
| 1 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.50 | 1.0 | 0.0 | 1.0 |
| 2 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 1.0 | 0.00 | 1.0 | 0.0 | 0.0 |
| 3 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.50 | 0.0 | 0.0 | 1.0 |
| 4 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.50 | 1.0 | 0.0 | 1.0 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 96 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.25 | 1.0 | 0.0 | 1.0 |
| 97 | 1.0 | 0.0 | 1.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 | 0.0 | 0.75 | 0.0 | 0.0 | 0.0 |
| 98 | 1.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.50 | 1.0 | 0.0 | 1.0 |
| 99 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.00 | 0.0 | 0.0 | 0.0 |
| 100 | 0.0 | 1.0 | 1.0 | 0.0 | 1.0 | 0.0 | 0.0 | 0.0 | 1.0 | 1.0 | 0.0 | 0.0 | 0.25 | 1.0 | 0.0 | 0.0 |
101 rows × 16 columns
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.7)
トレーニング
ロジスティック回帰
from sklearn.linear_model import LogisticRegression
log_model = LogisticRegression()
log_model.fit(X_train, y_train)
LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
intercept_scaling=1, l1_ratio=None, max_iter=100,
multi_class='auto', n_jobs=None, penalty='l2',
random_state=None, solver='lbfgs', tol=0.0001, verbose=0,
warm_start=False)
SVM
from sklearn.svm import SVC
svm_model = SVC(C=1.0)
svm_model.fit(X_train, y_train)
SVC(C=1.0, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,
decision_function_shape='ovr', degree=3, gamma='scale', kernel='rbf',
max_iter=-1, probability=False, random_state=None, shrinking=True,
tol=0.001, verbose=False)
ニューラルネット
from sklearn.neural_network import MLPClassifier
nn_model = MLPClassifier(hidden_layer_sizes=(64, 64))
nn_model.fit(X_train, y_train)
/usr/local/lib/python3.6/dist-packages/sklearn/neural_network/_multilayer_perceptron.py:571: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.
% self.max_iter, ConvergenceWarning)
MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,
beta_2=0.999, early_stopping=False, epsilon=1e-08,
hidden_layer_sizes=(64, 64), learning_rate='constant',
learning_rate_init=0.001, max_fun=15000, max_iter=200,
momentum=0.9, n_iter_no_change=10, nesterovs_momentum=True,
power_t=0.5, random_state=None, shuffle=True, solver='adam',
tol=0.0001, validation_fraction=0.1, verbose=False,
warm_start=False)
結果
log_acc = log_model.score(X_test, y_test)
svm_acc = svm_model.score(X_test, y_test)
nn_acc = nn_model.score(X_test, y_test)
print('Accuracy Results\n' + '*'*16)
print('Logistic Model:', log_acc)
print(' SVM Model:', svm_acc)
print(' NN Model:', nn_acc)
Accuracy Results
****************
Logistic Model: 0.9354838709677419
SVM Model: 0.9032258064516129
NN Model: 1.0
結果としてはニューラルネットが最も高い精度になりました。
ただ、データ自体がとても少ないのでそこは注意が必要だと思いました。