Last active
August 24, 2018 01:09
-
-
Save albrzykowski/5ec785850ded0da8b303e991f8ec62e0 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
''' | |
Classification of Autistic Spectrum Disorder based on: | |
https://archive.ics.uci.edu/ml/datasets/Autistic+Spectrum+Disorder+Screening+Data+for+Children++ dataset. | |
Only 10 answears are taking account as features. | |
''' | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
from sklearn.model_selection import train_test_split | |
from sklearn.svm import SVC | |
from sklearn.metrics import classification_report, confusion_matrix | |
from sklearn.model_selection import GridSearchCV | |
from sklearn.decomposition import PCA | |
import numpy as np | |
from sklearn.metrics import make_scorer | |
from sklearn.metrics import accuracy_score | |
''' | |
Using PCA: https://www.quora.com/Is-it-worth-trying-PCA-on-your-data-before-feeding-to-SVM | |
''' | |
df = pd.DataFrame.from_csv('train.csv') | |
pca = PCA(n_components=3) | |
principal_components = pca.fit_transform(df.iloc[:,0:9]) | |
''' | |
Plot principal components to select number of them to use | |
print(pca.explained_variance_ratio_) | |
plt.plot(pca.explained_variance_ratio_) | |
plt.show() | |
''' | |
pca_df = pd.DataFrame(data = principal_components | |
, columns = ['principal component 1', 'principal component 2', 'principal component 3']) | |
parameters = [ | |
{'kernel':['poly', 'rbf', 'sigmoid'], 'degree':[1,3], 'gamma':[2**-5, 2^1], 'C': [1,10]}, | |
] | |
X = pca_df.iloc[:,0:3] | |
cols = df['Class/ASD'] | |
y = pd.factorize(df['Class/ASD'])[0] + 1 | |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = .2) | |
svc = SVC() | |
clf = GridSearchCV(svc, parameters) | |
clf.fit(X_train, y_train) | |
y_pred = clf.predict(X_test) | |
print(confusion_matrix(y_test,y_pred)) | |
print(clf.best_params_) | |
print(clf.cv_results_) | |
print(classification_report(y_test,y_pred)) | |
''' | |
Output: | |
precision recall f1-score support | |
1 0.99 0.96 0.97 90 | |
2 0.88 0.97 0.92 30 | |
avg / total 0.96 0.96 0.96 120 | |
{'C': 10, 'degree': 1, 'gamma': 3, 'kernel': 'rbf'} | |
''' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment