Python RandomForestClassifier.score方法代碼示例

# 需要導入模塊: from sklearn.ensemble.forest import RandomForestClassifier [as 別名]
# 或者: from sklearn.ensemble.forest.RandomForestClassifier import score [as 別名]
def main(args):

    if args.analyse != None:
        train_data_x, test_data_x,train_data_y, test_data_y  = process_data(args.analyse)

        RT = RandomForestClassifier(n_estimators=100)
        RT.fit(train_data_x, train_data_y)
        print RT.score(test_data_x, test_data_y)

    return

# 需要導入模塊: from sklearn.ensemble.forest import RandomForestClassifier [as 別名]
# 或者: from sklearn.ensemble.forest.RandomForestClassifier import score [as 別名]
#Check if there is linear correlation between pixel<x> columns and label
#If yes, we should dive into the columns with correlation. Linear / logistic regression may work well with the data.
#In this case, makes sense that there is no correlation - higher pixel values does not mean that label value will be higher
#print "Correlation:", train.corr()["label"]

#Check that the algorithm used gives good accuracy by using part of the training set to validate
train_train, train_test=train_test_split(train, test_size=0.3)

#Train model
model=RandomForestClassifier(n_estimators = 100, oob_score = True, random_state =10, max_features = "auto", min_samples_leaf = 20)
#model=KNeighborsClassifier(n_neighbors=6)


#if getting this error, it is because a matrix with 1 column
#is being passed in when a 1d array is expected. ravel() will work.
#DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). if name == 'main':
#To resolve this error, convert label values to int or str as float is not a valid label-type
#raise ValueError("Unknown label type: %r" % y) ValueError: Unknown label type: array
#model.fit(train_train.ix[:,'pixel0':'pixel783'], np.asarray(train_train.ix[:,'label'].astype(int)))
#print "model.score:", model.score(train_test.ix[:,'pixel0':'pixel783'], np.asarray(train_test.ix[:,'label'].astype(int)))
#print "cross validation score:", cross_validation.cross_val_score(model, train_train.ix[:,'pixel0':'pixel783'], train_train.ix[:,'label'], cv=3)
model.fit(train_train.ix[:,'pixel0':'pixel783'], train_train.ix[:,'label'].values.ravel())
print "model.score", model.score(train_test.ix[:,'pixel0':'pixel783'], train_test.ix[:,'label'].values.ravel())


#Predict output
#predicted=model.predict(train_test.ix[:,'pixel0':'pixel783'])
#print predicted
#print "Accuracy: ", accuracy_score(train_test.ix[:,'label'].astype(int), predicted)

# 需要導入模塊: from sklearn.ensemble.forest import RandomForestClassifier [as 別名]
# 或者: from sklearn.ensemble.forest.RandomForestClassifier import score [as 別名]
#download the file
raw_data=urllib.urlopen(url)

#get data, add column names and index
feature_names=["times pregnant", "plasma glucose conc.", "distolic blood pressure (mm Hg)", "triceps skin fold thickness (mm)", "2-hour serum insulin (mu U/ml)", "body mass index (kg/m^2)", "diabetes pedigree function", "age (years)", "target"]
dataset=pd.DataFrame.from_csv(raw_data)
dataset=dataset.reset_index()
dataset.columns=feature_names

#split into train and test set
train, test=train_test_split(dataset, test_size=0.3)

#normalize data
df_scaled_train=pd.DataFrame(preprocessing.scale(train), columns=feature_names)
df_scaled_test=pd.DataFrame(preprocessing.scale(test), columns=feature_names)

model=RandomForestClassifier(n_estimators = 100, oob_score = True, random_state =10, max_features = "auto", min_samples_leaf = 20)

#train model
#if getting this error, it is because a matrix with 1 column
#is being passed in when a 1d array is expected. ravel() will work.
#DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel(). if name == 'main':
#To resolve this error, convert label values to int or str as float is not a valid label-type
#raise ValueError("Unknown label type: %r" % y) ValueError: Unknown label type: array
model.fit(df_scaled_train.ix[:,'times pregnant':'age (years)'], np.asarray(df_scaled_train.ix[:,'target'].astype(int)))
print "Accuracy:", model.score(df_scaled_test.ix[:,'times pregnant':'age (years)'], np.asarray(df_scaled_test.ix[:,'target'].astype(int)))

#predict output
predicted=model.predict(df_scaled_test.ix[:,'times pregnant':'age (years)'])
print predicted