def handle_debug_button(self, index): y = 10 print 'Debug button clicked : ' + str(index) d = mg.load_dataset('table_B') model = DataModel(d) view = MTableView(model) view.show()
import magellan as mg import numpy as np A = mg.load_dataset('table_A') B = mg.load_dataset('table_B') ob = mg.OverlapBlocker() C = ob.block_tables(A, B, 'address', 'address', word_level=False, qgram=3, overlap_size=3, l_output_attrs=['name', 'name']) D = ob.block_candset(C, 'name', 'name', overlap_size=1) E = ob.block_tuples(A.ix[1], B.ix[1], 'name', 'name', overlap_size=1) print C print "-----" print D print " ----- " print E
import magellan as mg A = mg.load_dataset('table_A', 'id') B = mg.load_dataset('table_B', 'id') Ap, Bp = mg.down_sample(A, B, 5, 2) print Ap print Bp
import sys import magellan as mg from magellan.gui.debug_gui_base import vis_debug_dt sys.path.append('/Users/Pradap/Documents/Research/Python-Package/enrique/') mg.init_jvm() A = mg.load_dataset('table_A') B = mg.load_dataset('table_B') ab = mg.AttrEquivalenceBlocker() C = ab.block_tables(A, B, 'zipcode', 'zipcode', ['name'], ['name']) L = mg.read_csv('label_demo.csv', ltable=A, rtable=B) feat_table = mg.get_features_for_matching(A, B) G = mg.extract_feature_vecs(L, feature_table=feat_table, attrs_after='gold') S = mg.train_test_split(G, 8, 7) dt = mg.DTMatcher(name='DecisionTree') dt.fit(table = S['train'], exclude_attrs=['_id', 'ltable.ID', 'rtable.ID', 'gold'], target_attr='gold') dt.predict(table=S['test'], exclude_attrs=['_id', 'ltable.ID', 'rtable.ID', 'gold'], target_attr='predicted', append=True) d = mg.eval_matches(S['test'], 'gold', 'predicted') vis_debug_dt(dt, d, S['test'], exclude_attrs=['_id', 'ltable.ID', 'rtable.ID', 'gold'], feat_table=feat_table) print "Hi"
def change_table_contents(self): d = mg.load_dataset('table_B') self.model = DataModel(d) self.view.set_model(self.model) self.view.paint_gui()
self.setLayout(layout) # QApplication.setStyle(QStyleFactory.create('motif')) def change_table_contents(self): d = mg.load_dataset('table_B') self.model = DataModel(d) self.view.set_model(self.model) self.view.paint_gui() # model = DataModel(d) # view = MTableView(model) # view.show() import magellan as mg import sys app = mg._viewapp d = mg.load_dataset('table_A') # w = MWidget(d) w = MurWidget(d) w.show() (app.exec_())
import magellan as mg A = mg.load_dataset('table_A', key='ID') A1= A[['ID']] d = mg.get_attr_types(A1) print(d)
self.debug_widget = TreeViewWithLabel(self, "Tree details", type="dt") layout = QtGui.QHBoxLayout() splitter1 = QtGui.QSplitter(QtCore.Qt.Vertical) splitter1.addWidget(self.left_tuple_widget) splitter1.addWidget(self.right_tuple_widget) splitter2 = QtGui.QSplitter(QtCore.Qt.Horizontal) splitter2.addWidget(splitter1) splitter2.addWidget(self.debug_widget) layout.addWidget(splitter2) self.setLayout(layout) import magellan as mg from collections import OrderedDict app = mg._viewapp dataframe = mg.load_dataset('table_A') b = mg.load_dataset('table_B') metric_data = OrderedDict() metric_data['Precision'] = 0.95 metric_data['Recall'] = 0.93 metric_data['F1'] = 0.94 metric_data['Num. False Positives'] = 5 metric_data['Num. False Negatives'] = 6 m = MainWindowManager(metric_data, dataframe, b) m.show() app.exec_()
# coding=utf-8 import magellan as mg A = mg.load_dataset('table_A', key='ID') B = mg.load_dataset('table_B', key='ID') F = mg.get_features_for_blocking(A, B) print(F)
# self.debug_widget = DictTableViewWithLabel(self, self.debug_result, 'Debug Result') self.debug_widget = TreeViewWithLabel(self, "Tree details", type="dt") layout = QtGui.QHBoxLayout() splitter1 = QtGui.QSplitter(QtCore.Qt.Vertical) splitter1.addWidget(self.left_tuple_widget) splitter1.addWidget(self.right_tuple_widget) splitter2 = QtGui.QSplitter(QtCore.Qt.Horizontal) splitter2.addWidget(splitter1) splitter2.addWidget(self.debug_widget) layout.addWidget(splitter2) self.setLayout(layout) import magellan as mg from collections import OrderedDict app = mg._viewapp dataframe = mg.load_dataset('table_A') b = mg.load_dataset('table_B') metric_data = OrderedDict() metric_data['Precision'] = 0.95 metric_data['Recall'] = 0.93 metric_data['F1'] = 0.94 metric_data['Num. False Positives'] = 5 metric_data['Num. False Negatives'] = 6 m = MainWindowManager(metric_data, dataframe, b) m.show() app.exec_()