Python qda.QDA类代码示例

class RegularizedQDA:
  """
    Three types of regularization are possible:
    - regularized the covariance of a class toward the 
      average variance within that class
    - regularize the covariance of a class toward the
      pooled covariance across all classes
    - add some constant amount of variance to each feature
  """
  def __init__(self, avg_weight = 0.1, pooled_weight = 0, extra_variance = 0):
    self.avg_weight = avg_weight
    self.pooled_weight = pooled_weight
    self.extra_variance = extra_variance 
    self.model = QDA()
    
  def fit(self, X, Y):
    self.model.fit(X,Y)
    I = np.eye(X.shape[1])
    a = self.avg_weight
    p = self.pooled_weight
    ev = self.extra_variance 
    original_weight = 1.0 - a - p
    scaled_pooled_cov = p * np.cov(X.T)
    assert scaled_pooled_cov.shape == I.shape
    assert all([C.shape == I.shape for C in self.model.rotations])
    self.model.rotations = \
      [original_weight * C + \
       a * np.mean(np.diag(C)) * I + \
       scaled_pooled_cov + ev * I \
       for C in self.model.rotations] 
      
  def predict(self, X):
    return self.model.predict(X)

    def test_all_methods(self):
        x_cols = ["Lag2"]
        formula = "Direction~Lag2"
        # print self.df.shape[0]
        train_data = self.df.ix[(self.df["Year"] >= 1990) & (self.df["Year"] <= 2008), :]
        # print train_data.shape[0]
        """ (d) logistic"""
        model = smf.glm(formula, data=train_data, family=sm.families.Binomial())
        result = model.fit()
        test_data = self.df.ix[self.df["Year"] > 2008, :]
        probs = Series(result.predict(sm.add_constant(test_data[["Lag2"]])))
        pred_values = probs.map(lambda x: "Down" if x > 0.5 else "Up")
        tp.output_table(pred_values.values, test_data[self.y_col].values)

        train_X = train_data[x_cols].values
        train_y = train_data[self.y_col].values
        test_X = test_data[x_cols].values
        test_y = test_data[self.y_col].values
        """ (e) LDA """
        lda_res = LDA().fit(train_X, train_y)
        pred_y = lda_res.predict(test_X)
        tp.output_table(pred_y, test_y)
        """ (f) QDA """
        qda_res = QDA().fit(train_X, train_y)
        pred_y = qda_res.predict(test_X)
        tp.output_table(pred_y, test_y)
        """ (g) KNN """
        clf = neighbors.KNeighborsClassifier(1, weights="uniform")
        clf.fit(train_X, train_y)
        pred_y = clf.predict(test_X)
        tp.output_table(pred_y, test_y)
        """ (h) logistic and LDA """
        """ (i) Is the purpose of the last question going through all methods with no direction?"""

class SNPForecastingStrategy(Strategy):
	def __init__(self,symbol,bars):
		self.symbol=symbol
		self.bars=bars
		self.create_periods()
		self.fit_model()

	def create_periods(self):
		self.start_train=datetime.datetime(2001,1,10)
		self.start_test=datetime.datetime(2005,1,1)
		self.end_period=datetime.datetime(2005,12,31)

	def fit_model(self):
		snpret=create_lagged_series(self.symbol,self.start_train,self.end_period,lags=5)
		X=snpret[['Lag1','Lag2']]
		Y=snpret['Direction']
		X_train=X[X.index<self.start_test]
		Y_train=Y[Y.index<self.start_test]
		self.predictors=X[X.index>=self.start_test]
		self.model=QDA()
		self.model.fit(X_train,Y_train)

	def generate_signals(self):
		signals=pd.DataFrame(index=self.bars.index)
		signals['signal']=0.0
		signals['signal']=self.model.predict(self.predictors)
		signals['signal'][0:5]=0.0
		signals['positions']=signals['signal'].diff()
		return signals

class SNPForecastingStrategy(Strategy):
    """    
    Requires:
    symbol - A stock symbol on which to form a strategy on.
    bars - A DataFrame of bars for the above symbol."""

    def __init__(self, symbol, bars):
        self.symbol = symbol
        self.bars = bars
        self.create_periods()
        self.fit_model()

    def create_periods(self):
        """Create training/test periods."""
        self.start_train = datetime.datetime(2001,1,10)
        self.start_test = datetime.datetime(2005,1,1)
        self.end_period = datetime.datetime(2005,12,31)

    def fit_model(self):
        """Fits a Quadratic Discriminant Analyser to the
        US stock market index (^GPSC in Yahoo)."""
        # Create a lagged series of the S&P500 US stock market index
        snpret = create_lagged_series(self.symbol, self.start_train, 
                                      self.end_period, lags=5) 

        # Use the prior two days of returns as 
        # predictor values, with direction as the response
        X = snpret[["Lag1","Lag2"]]
        y = snpret["Direction"]

        # Create training and test sets
        X_train = X[X.index < self.start_test]
        y_train = y[y.index < self.start_test]

        # Create the predicting factors for use 
        # in direction forecasting
        self.predictors = X[X.index >= self.start_test]

        # Create the Quadratic Discriminant Analysis model
        # and the forecasting strategy
        self.model = QDA()
        self.model.fit(X_train, y_train)

    def generate_signals(self):
        """Returns the DataFrame of symbols containing the signals
        to go long, short or hold (1, -1 or 0)."""
        signals = pd.DataFrame(index=self.bars.index)
        signals['signal'] = 0.0       

        # Predict the subsequent period with the QDA model
        signals['signal'] = self.model.predict(self.predictors)

        # Remove the first five signal entries to eliminate
        # NaN issues with the signals DataFrame
        signals['signal'][0:5] = 0.0
        signals['positions'] = signals['signal'].diff() 

        return signals

def performSVMClass(X_train, y_train, X_test, y_test, parameters, fout, savemodel):
	"""
	SVM binary classification
	"""
	clf = QDA()
	clf.fit(X_train, y_train)

	accuracy = clf.score(X_test, y_test)
	return accuracy

def performQDAClass(X_train, y_train, X_test, y_test):
    """
    Gradient Tree Boosting binary Classification
    """
    clf = QDA()
    clf.fit(X_train, y_train)
    accuracy = clf.score(X_test, y_test)
    #auc = roc_auc_score(y_test, clf.predict(X_test))
    return accuracy

def qda(data,labels,n,v_type):
	train_data,train_labels,test_data,test_labels = split_data(data,labels,v_type)

	clf = QDA()
	clf.fit(train_data, train_labels)
	y_pred = clf.predict(test_data)
	pure_accuracy_rate = len([y_pred[x] for x in range(len(y_pred)) if y_pred[x] == test_labels[x]])/float(len(test_labels))
	report = classification_report(y_pred, test_labels, target_names=rock_names)
	cm = confusion_matrix(test_labels, y_pred)
	return pure_accuracy_rate,report,y_pred,test_labels,test_data,clf,cm,"QDA"

	def QDA(self,membership,group_labels=None,std=3,ellipses=True,dpi=300,fontsize=10,MD=False,
	        legend=False, numbered=False,of='pdf'):
		self.type = 'QDA'
		membership = membership.astype(int)
		qda = QDA()
		self.fit = qda.fit(self.data, membership).predict(self.data)
		if ellipses:
			self.getEllipses(std,membership)
		self.PlotXDA(membership,group_labels=group_labels,std=std,ellipses=ellipses,dpi=dpi,
		             fontsize=fontsize,MD=MD,legend=legend,numbered=numbered,of=of)
		self.Store()

def qda_predict(train_data, test_data, train_cat, xx, yy):
    # QDA CLASSIFIER
    qda_classifier = QDA()

    qda_fit = qda_classifier.fit(train_data, train_cat)
    predicted = qda_fit.predict(test_data)

    contour = qda_fit.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
    contour = contour.reshape(xx.shape)

    return predicted, contour

def get_QDA(Xtrain, Xtest, Ytrain, Ytest):
    qda = QDA()
    qda.fit(Xtrain,Ytrain)
#    predLabels = qda.predict(Xtest)
#    print("Classification Rate Test QDA: " + str(np.mean(Ytest==predLabels)*100) + " %")
    scores = np.empty((4))
    scores[0] = qda.score(Xtrain,Ytrain)
    scores[1] = qda.score(Xtest,Ytest)
    print('QDA, train: {0:.02f}% '.format(scores[0]*100))
    print('QDA, test: {0:.02f}% '.format(scores[1]*100))
    return qda

def train_qda(X, y, priors=None, reg_param=0.0):
    """
    Builds a quadratic discriminant analysis model

    Returns:
    clf: Fitted QDA model
    """
    clf = QDA(priors=priors,
              reg_param=reg_param)
    clf = clf.fit(X,y)
    print 'Quadratic Discriminant Analysis completed!'
    return clf

def QuadraticDiscriminantAnalysis(x_train, y_train, x_cv, y_cv):
	"""
	Quadratic Discriminant Analysis Classifier
	"""
	print "Quadratic Discriminant Analysis"
	clfr = QDA()
	clfr.fit(x_train, y_train)
	#print 'Accuracy in training set: %f' % clfr.score(x_train, y_train)
	#if y_cv != None:
		#print 'Accuracy in cv set: %f' % clfr.score(x_cv, y_cv)
	
	return clfr

def train_classifier(xTrain_s, yTrain_s, kwargs):
    """
    Train a naive baise classifier on xTrain and yTrain and return the trained
    classifier
    """
    if type(xTrain_s) != list:
        classifier_s = QDA(**kwargs)
        classifier_s.fit(xTrain_s, yTrain_s)

    else:
        classifier_s = train_classifier_8(xTrain_s, yTrain_s, kwargs)

    return classifier_s

def QDA_onFullDataset():
    #Parsing Full training dataset
    XFull = common.parseFile('../UCI HAR Dataset/train/X_train.txt')
    YFull = common.parseFile('../UCI HAR Dataset/train/y_train.txt')

    #Parsing Full testing dataset
    XFullTest = common.parseFile('../UCI HAR Dataset/test/X_test.txt')
    YFullTest = common.parseFile('../UCI HAR Dataset/test/y_test.txt')

    #Fitting data using QDA classifier
    clf = QDA()
    clf.fit(XFull, YFull.flatten())

    #Testing the results
    precision,recall,fscore = common.checkAccuracy(clf.predict(XFullTest),YFullTest,[1,2,3,4,5,6])
    print fscore

 def fit_model(self):
   """Fits a Quadratic Discriminat Analyser to the US
   sock market index (^GPSC in Yahoo)."""
   # Create a laggged series of the S&P500 US stock market index
   
   snpret =  create_lagged_series(self.symbol, self.start_train,
               self.end_period, lags=5)
   
   # Use the prior two days of returns as 
   # predictor value, with direction as the response
   X = snpret[["Lag1", "Lag2"]]
   y = snpret["Direction"]
   
   # Create training and test sets
   X_train = X[X.index < self.start_test]
   y_train = y[y.index < self.start_test]
   
   # Create the prediciting factors for use
   # in direction forecasting.
   self.predictors = X[X.index >= self.start_test]
   
   # Create the Quadractic Discriminant Analysis model
   # and the forcasting strategy
   self.model = QDA()
   self.model.fit(X_train, y_train)