From b41f81eb7008cfbc00e1d0c49a56e3b0ba2af137 Mon Sep 17 00:00:00 2001
From: Sahil Kang <sahil.kang@asilaycomputing.com>
Date: Wed, 22 Jun 2016 23:13:38 -0700
Subject: [PATCH] Use logging.info instead of print (#6929)

---
 sklearn/datasets/california_housing.py    | 3 ++-
 sklearn/datasets/kddcup99.py              | 2 +-
 sklearn/datasets/olivetti_faces.py        | 3 ++-
 sklearn/datasets/species_distributions.py | 7 ++++---
 sklearn/datasets/twenty_newsgroups.py     | 8 ++++----
 5 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/sklearn/datasets/california_housing.py b/sklearn/datasets/california_housing.py
index ee1bf5bde4514..d6cdc0414143b 100644
--- a/sklearn/datasets/california_housing.py
+++ b/sklearn/datasets/california_housing.py
@@ -26,6 +26,7 @@
 from os.path import exists
 from os import makedirs
 import tarfile
+import logging
 
 try:
     # Python 2
@@ -90,7 +91,7 @@ def fetch_california_housing(data_home=None, download_if_missing=True):
         makedirs(data_home)
     filepath = _pkl_filepath(data_home, TARGET_FILENAME)
     if not exists(filepath):
-        print('downloading Cal. housing from %s to %s' % (DATA_URL, data_home))
+        logging.info('downloading Cal. housing from %s to %s' % (DATA_URL, data_home))
         archive_fileobj = BytesIO(urlopen(DATA_URL).read())
         fileobj = tarfile.open(
             mode="r:gz",
diff --git a/sklearn/datasets/kddcup99.py b/sklearn/datasets/kddcup99.py
index 06b97da950b8d..ea18700511483 100644
--- a/sklearn/datasets/kddcup99.py
+++ b/sklearn/datasets/kddcup99.py
@@ -329,7 +329,7 @@ def _fetch_brute_kddcup99(subset=None, data_home=None,
                 line = line.decode()
             Xy.append(line.replace('\n', '').split(','))
         file_.close()
-        print('extraction done')
+        logging.info('extraction done')
         Xy = np.asarray(Xy, dtype=object)
         for j in range(42):
             Xy[:, j] = Xy[:, j].astype(DT[j])
diff --git a/sklearn/datasets/olivetti_faces.py b/sklearn/datasets/olivetti_faces.py
index 978a00db3ca14..dfbc09ff8a89b 100644
--- a/sklearn/datasets/olivetti_faces.py
+++ b/sklearn/datasets/olivetti_faces.py
@@ -25,6 +25,7 @@
 from io import BytesIO
 from os.path import exists
 from os import makedirs
+import logging
 try:
     # Python 2
     import urllib2
@@ -111,7 +112,7 @@ def fetch_olivetti_faces(data_home=None, shuffle=False, random_state=0,
         makedirs(data_home)
     filepath = _pkl_filepath(data_home, TARGET_FILENAME)
     if not exists(filepath):
-        print('downloading Olivetti faces from %s to %s'
+        logging.info('downloading Olivetti faces from %s to %s'
               % (DATA_URL, data_home))
         fhandle = urlopen(DATA_URL)
         buf = BytesIO(fhandle.read())
diff --git a/sklearn/datasets/species_distributions.py b/sklearn/datasets/species_distributions.py
index 3d10528e7b682..a6507e295d1ad 100644
--- a/sklearn/datasets/species_distributions.py
+++ b/sklearn/datasets/species_distributions.py
@@ -38,6 +38,7 @@
 from io import BytesIO
 from os import makedirs
 from os.path import exists
+import logging
 
 try:
     # Python 2
@@ -222,7 +223,7 @@ def fetch_species_distributions(data_home=None,
     archive_path = _pkl_filepath(data_home, DATA_ARCHIVE_NAME)
 
     if not exists(archive_path):
-        print('Downloading species data from %s to %s' % (SAMPLES_URL,
+        logging.info('Downloading species data from %s to %s' % (SAMPLES_URL,
                                                           data_home))
         X = np.load(BytesIO(urlopen(SAMPLES_URL).read()))
 
@@ -233,7 +234,7 @@ def fetch_species_distributions(data_home=None,
             if 'test' in f:
                 test = _load_csv(fhandle)
 
-        print('Downloading coverage data from %s to %s' % (COVERAGES_URL,
+        logging.info('Downloading coverage data from %s to %s' % (COVERAGES_URL,
                                                            data_home))
 
         X = np.load(BytesIO(urlopen(COVERAGES_URL).read()))
@@ -241,7 +242,7 @@ def fetch_species_distributions(data_home=None,
         coverages = []
         for f in X.files:
             fhandle = BytesIO(X[f])
-            print(' - converting', f)
+            logging.info(' - converting', f)
             coverages.append(_load_coverage(fhandle))
         coverages = np.asarray(coverages, dtype=dtype)
 
diff --git a/sklearn/datasets/twenty_newsgroups.py b/sklearn/datasets/twenty_newsgroups.py
index 524d38d6c1ec1..bc1e9a69fabe8 100644
--- a/sklearn/datasets/twenty_newsgroups.py
+++ b/sklearn/datasets/twenty_newsgroups.py
@@ -212,10 +212,10 @@ def fetch_20newsgroups(data_home=None, subset='train', categories=None,
                 compressed_content, 'zlib_codec')
             cache = pickle.loads(uncompressed_content)
         except Exception as e:
-            print(80 * '_')
-            print('Cache loading failed')
-            print(80 * '_')
-            print(e)
+            logging.info(80 * '_')
+            logging.info('Cache loading failed')
+            logging.info(80 * '_')
+            logging.info(e)
 
     if cache is None:
         if download_if_missing: