|
1 |
train.info() |
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
PassengerId 891 non-null int64
Survived 891 non-null int64
Pclass 891 non-null int64
Name 891 non-null object
Sex 891 non-null object
Age 714 non-null float64
SibSp 891 non-null int64
Parch 891 non-null int64
Ticket 891 non-null object
Fare 891 non-null float64
Cabin 204 non-null object
Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.6+ KB
None
決定木
|
1 2 3 4 5 6 7 8 9 10 11 12 13 |
train_X = df.drop('Survived', axis=1) train_y = df.Survived (train_X, test_X ,train_y, test_y) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666) #決定木 clf = DecisionTreeClassifier(random_state=0) clf = clf.fit(train_X, train_y) pred = clf.predict(test_X) #決定木のモデルスコア fpr, tpr, thresholds = roc_curve(test_y, pred, pos_label=1) auc(fpr, tpr) accuracy_score(pred, test_y) |
ランダムフォレスト
|
1 2 3 4 5 6 7 8 9 10 11 12 13 |
train_X = df.drop('Survived', axis=1) train_y = df.Survived ( train_X, test_X ,train_y, test_y ) = train_test_split(train_X, train_y, test_size = 0.3, random_state = 666) #ランダムフォレスト from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(random_state=0) clf = clf.fit(train_X, train_y) pred = clf.predict(test_X) fpr, tpr, thresholds = roc_curve(test_y, pred, pos_label=1) auc(fpr, tpr) accuracy_score(pred, test_y) |
公式ドキュメント
sklearn.tree.DecisionTreeClassifier — scikit-learn 0.19.1 documentation
どの要素が強く影響を与えているかを確認
|
1 2 3 4 5 6 7 8 9 10 11 12 13 |
import matplotlib.pyplot as plt import numpy as np %matplotlib inline features = train_X.columns importances = clf.feature_importances_ indices = np.argsort(importances) plt.figure(figsize=(6,6)) plt.barh(range(len(indices)), importances[indices], color='b', align='center') plt.yticks(range(len(indices)), features[indices]) plt.show() |
最初にインストール
|
1 2 |
pip install pydotplus brew install graphviz |
|
1 2 3 4 5 6 7 8 9 10 11 |
#可視化 import pydotplus from IPython.display import Image from graphviz import Digraph from sklearn.externals.six import StringIO dot_data = StringIO() tree.export_graphviz(clf, out_file=dot_data,feature_names=train_X.columns, max_depth=3) graph = pydotplus.graph_from_dot_data(dot_data.getvalue()) graph.write_pdf("graph.pdf") Image(graph.create_png()) |
モデルスコア1に近いほど精度が高い
|
1 2 3 4 5 6 |
from sklearn.metrics import (roc_curve, auc, accuracy_score) pred = clf.predict(test_X) fpr, tpr, thresholds = roc_curve(test_y, pred, pos_label=1) auc(fpr, tpr) accuracy_score(pred, test_y) |
インポート用コード
|
1 2 3 4 5 6 7 8 |
pd.read_csv(filename) # From a CSV file pd.read_table(filename) # From a delimited text file (like TSV) pd.read_excel(filename) # From an Excel file pd.read_sql(query, connection_object) # Reads from a SQL table/database pd.read_json(json_string) # Reads from a JSON formatted string, URL or file. pd.read_html(url) # Parses an html URL, string or file and extracts tables to a list of dataframes pd.read_clipboard() # Takes the contents of your clipboard and passes it to read_table() pd.DataFrame(dict) # From a dict, keys for columns names, values for data as lists |