udacity 机器学习课程 project2

准确率

import sys
from class_vis import prettyPicture
from prep_terrain_data import makeTerrainData

import matplotlib.pyplot as plt
import copy
import numpy as np
import pylab as pl


features_train, labels_train, features_test, labels_test = makeTerrainData()


########################## SVM #################################
### we handle the import statement and SVC creation for you here
from sklearn.svm import SVC
clf = SVC(kernel="linear")
clf.fit(features_train, labels_train)

#### now your job is to fit the classifier
#### using the training features/labels, and to
#### make a set of predictions on the test data

predictions = clf.predict(features_test)

#### store your predictions in a list named pred

pred = predictions



from sklearn.metrics import accuracy_score
acc = accuracy_score(pred, labels_test)

def submitAccuracy():
    return acc

把非数字的列特征 转换成数字

def preprocess_features(X):
    ''' Preprocesses the student data and converts non-numeric binary variables into
        binary (0/1) variables. Converts categorical variables into dummy variables. '''
    
    # Initialize new output DataFrame可
    output = pd.DataFrame(index = X.index)

    # Investigate each feature column for the data
    for col, col_data in X.iteritems():
        
        # If data type is non-numeric, replace all yes/no values with 1/0
        if col_data.dtype == object:
            col_data = col_data.replace(['yes', 'no'], [1, 0])

        # If data type is categorical, convert to dummy variables
        if col_data.dtype == object:
            # Example: 'school' => 'school_GP' and 'school_MS'
            col_data = pd.get_dummies(col_data, prefix = col)  
        
        # Collect the revised columns
        output = output.join(col_data)
    
    return output

X_all = preprocess_features(X_all)
print "Processed feature columns ({} total features):
{}".format(len(X_all.columns), list(X_all.columns))