Remove text loading in basic walk through demo. (#7753)

demo/guide-python/basic_walkthrough.py

@@ -1,50 +1,65 @@
 """
 Getting started with XGBoost
 ============================
+
+This is a simple example of using the native XGBoost interface, there are other
+interfaces in the Python package like scikit-learn interface and Dask interface.
+
+
+See :doc:`/python/python_intro` and :doc:`/tutorials/index` for other references.
+
 """
 import numpy as np
-import scipy.sparse
 import pickle
 import xgboost as xgb
 import os
 
+from sklearn.datasets import load_svmlight_file
+
 # Make sure the demo knows where to load the data.
 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
 XGBOOST_ROOT_DIR = os.path.dirname(os.path.dirname(CURRENT_DIR))
-DEMO_DIR = os.path.join(XGBOOST_ROOT_DIR, 'demo')
+DEMO_DIR = os.path.join(XGBOOST_ROOT_DIR, "demo")
 
-# simple example
-# load file from text file, also binary buffer generated by xgboost
-dtrain = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train?indexing_mode=1'))
-dtest = xgb.DMatrix(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.test?indexing_mode=1'))
+# X is a scipy csr matrix, XGBoost supports many other input types,
+X, y = load_svmlight_file(os.path.join(DEMO_DIR, "data", "agaricus.txt.train"))
+dtrain = xgb.DMatrix(X, y)
+# validation set
+X_test, y_test = load_svmlight_file(os.path.join(DEMO_DIR, "data", "agaricus.txt.test"))
+dtest = xgb.DMatrix(X_test, y_test)
 
 # specify parameters via map, definition are same as c++ version
-param = {'max_depth': 2, 'eta': 1, 'objective': 'binary:logistic'}
+param = {"max_depth": 2, "eta": 1, "objective": "binary:logistic"}
 
 # specify validations set to watch performance
-watchlist = [(dtest, 'eval'), (dtrain, 'train')]
+watchlist = [(dtest, "eval"), (dtrain, "train")]
+# number of boosting rounds
 num_round = 2
-bst = xgb.train(param, dtrain, num_round, watchlist)
+bst = xgb.train(param, dtrain, num_boost_round=num_round, evals=watchlist)
 
-# this is prediction
+# run prediction
 preds = bst.predict(dtest)
 labels = dtest.get_label()
-print('error=%f' %
-      (sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) /
-       float(len(preds))))
-bst.save_model('0001.model')
+print(
+    "error=%f"
+    % (
+        sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i])
+        / float(len(preds))
+    )
+)
+bst.save_model("model-0.json")
 # dump model
-bst.dump_model('dump.raw.txt')
+bst.dump_model("dump.raw.txt")
 # dump model with feature map
-bst.dump_model('dump.nice.txt', os.path.join(DEMO_DIR, 'data/featmap.txt'))
+bst.dump_model("dump.nice.txt", os.path.join(DEMO_DIR, "data/featmap.txt"))
 
 # save dmatrix into binary buffer
-dtest.save_binary('dtest.buffer')
+dtest.save_binary("dtest.dmatrix")
 # save model
-bst.save_model('xgb.model')
+bst.save_model("model-1.json")
 # load model and data in
-bst2 = xgb.Booster(model_file='xgb.model')
-dtest2 = xgb.DMatrix('dtest.buffer')
+bst2 = xgb.Booster(model_file="model-1.json")
+dtest2 = xgb.DMatrix("dtest.dmatrix")
 preds2 = bst2.predict(dtest2)
 # assert they are the same
 assert np.sum(np.abs(preds2 - preds)) == 0
@@ -56,40 +71,3 @@ bst3 = pickle.loads(pks)
 preds3 = bst3.predict(dtest2)
 # assert they are the same
 assert np.sum(np.abs(preds3 - preds)) == 0
-
-###
-# build dmatrix from scipy.sparse
-print('start running example of build DMatrix from scipy.sparse CSR Matrix')
-labels = []
-row = []
-col = []
-dat = []
-i = 0
-for l in open(os.path.join(DEMO_DIR, 'data', 'agaricus.txt.train')):
-    arr = l.split()
-    labels.append(int(arr[0]))
-    for it in arr[1:]:
-        k, v = it.split(':')
-        row.append(i)
-        col.append(int(k))
-        dat.append(float(v))
-    i += 1
-csr = scipy.sparse.csr_matrix((dat, (row, col)))
-dtrain = xgb.DMatrix(csr, label=labels)
-watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-bst = xgb.train(param, dtrain, num_round, watchlist)
-
-print('start running example of build DMatrix from scipy.sparse CSC Matrix')
-# we can also construct from csc matrix
-csc = scipy.sparse.csc_matrix((dat, (row, col)))
-dtrain = xgb.DMatrix(csc, label=labels)
-watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-bst = xgb.train(param, dtrain, num_round, watchlist)
-
-print('start running example of build DMatrix from numpy array')
-# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix
-# in internal implementation then convert to DMatrix
-npymat = csr.todense()
-dtrain = xgb.DMatrix(npymat, label=labels)
-watchlist = [(dtest, 'eval'), (dtrain, 'train')]
-bst = xgb.train(param, dtrain, num_round, watchlist)

doc/python/python_intro.rst

@@ -45,6 +45,7 @@ including:
 - XGBoost binary buffer file.
 - LIBSVM text format file
 - Comma-separated values (CSV) file
+- Arrow table.
 
 (See :doc:`/tutorials/input_format` for detailed description of text input format.)
 

python-package/xgboost/core.py

@@ -565,12 +565,14 @@ class DMatrix:  # pylint: disable=too-many-instance-attributes
         """Parameters
         ----------
         data : os.PathLike/string/numpy.array/scipy.sparse/pd.DataFrame/
-               dt.Frame/cudf.DataFrame/cupy.array/dlpack
+               dt.Frame/cudf.DataFrame/cupy.array/dlpack/arrow.Table
+
             Data source of DMatrix.
-            When data is string or os.PathLike type, it represents the path
-            libsvm format txt file, csv file (by specifying uri parameter
-            'path_to_csv?format=csv'), or binary file that xgboost can read
-            from.
+
+            When data is string or os.PathLike type, it represents the path libsvm
+            format txt file, csv file (by specifying uri parameter
+            'path_to_csv?format=csv'), or binary file that xgboost can read from.
+
         label : array_like
             Label of the training data.
         weight : array_like