Minor: unify data files location at data

Author: basicthinker

data/README

@@ -0,0 +1,8 @@
+The data structure of fs-patch.pickle:
+
+The data structure of jira-issues.pickle:
+
+A nested dictionary [repo_name][issue_id]['commits'/'title'/'description'/'comment'/'type'/'priority']
+
+'commits' indexes a list of commit hashes related to the issue.
+

notebooks/data/fs-patch.pickle

@@ -34,7 +34,7 @@
    "outputs": [],
    "source": [
     "import pickle\n",
-    "datasets = pickle.load(open('data/fs-patch.pickle', 'rb'))"
+    "datasets = pickle.load(open('../data/fs-patch.pickle', 'rb'))"
    ]
   },
   {

notebooks/fs_patch_classification.ipynb

@@ -167,7 +167,7 @@
    "outputs": [],
    "source": [
     "import pickle\n",
-    "pickle.dump(datasets, open('data/fs-patch.pickle', 'wb'), True)"
+    "pickle.dump(datasets, open('../data/fs-patch.pickle', 'wb'), True)"
    ]
   },
   {
@@ -189,12 +189,12 @@
     "import dicttoxml\n",
     "from xml.dom.minidom import parseString\n",
     "\n",
-    "datasets = pickle.load(open('data/fs-patch.pickle', 'rb'))\n",
+    "datasets = pickle.load(open('../data/fs-patch.pickle', 'rb'))\n",
     "fss = ['ext3', 'ext4', 'btrfs', 'xfs', 'jfs', 'reiserfs']\n",
     "for fs in fss:\n",
     "    xml = dicttoxml.dicttoxml(datasets[fs], custom_root=fs)\n",
     "    dom = parseString(xml)\n",
-    "    file = open('data/' + fs + '-patch.xml', 'w')\n",
+    "    file = open('../data/' + fs + '-patch.xml', 'w')\n",
     "    file.write(dom.toprettyxml())\n",
     "    file.close()"
    ]

notebooks/process_fs_patch.ipynb

@@ -172,7 +172,7 @@
    "outputs": [],
    "source": [
     "def getInfoFromXML(fromDir, path):\n",
-    "    toDir = \"./data/desAndCom/\"\n",
+    "    toDir = \"../data/desAndCom/\"\n",
     "    fromFile = os.path.join('%s%s' % (fromDir, path))\n",
     "    toFile = os.path.join('%s%s' % (toDir, path))\n",
     "    #print fromFile, toFile, path\n",
@@ -262,9 +262,9 @@
     "    return numFiles\n",
     "            #print allDir\n",
     "\n",
-    "filePath = \"./data/spark-issues/\"\n",
+    "filePath = \"../data/spark-issues/\"\n",
     "#eachFile(filePath)\n",
-    "numFiles = getUsefulInfo(filePath)             #write all useful information to ./data/desAndCom\n",
+    "numFiles = getUsefulInfo(filePath)             #write all useful information to ../data/desAndCom\n",
     "numFiles"
    ]
   },
@@ -319,8 +319,8 @@
    },
    "outputs": [],
    "source": [
-    "fileList =  os.listdir(\"./data/desAndCom/\")\n",
-    "fileDir = \"./data/desAndCom/\"\n",
+    "fileList =  os.listdir(\"../data/desAndCom/\")\n",
+    "fileDir = \"../data/desAndCom/\"\n",
     "files = []\n",
     "for tempFile in fileList:\n",
     "    if \"ipynb\" in tempFile:\n",
@@ -404,8 +404,8 @@
    },
    "outputs": [],
    "source": [
-    "fileList = os.listdir(\"./data/desAndCom/\")\n",
-    "fileDir = \"./data/clearFiles/\"\n",
+    "fileList = os.listdir(\"../data/desAndCom/\")\n",
+    "fileDir = \"../data/clearFiles/\"\n",
     "files = []\n",
     "for tempFile in fileList:\n",
     "    if \"ipynb\" in tempFile:\n",
@@ -623,7 +623,7 @@
    },
    "outputs": [],
    "source": [
-    "testFilenames = sorted(glob('./data/clearFiles/*'))\n",
+    "testFilenames = sorted(glob('../data/clearFiles/*'))\n",
     "#print testFilenames\n",
     "\n",
     "# While we're at it, let's make a list of the lengths, so we can use them to plot dot sizes. \n",

notebooks/tf-idf-Spark.ipynb

@@ -145,7 +145,7 @@
     "import pickle\n",
     "\n",
     "# Download the test pickle file from https://share.weiyun.com/9ecbf5799502577312baa6b17a584b17\n",
-    "datasets = pickle.load(open('data/jira-issues-test.pickle', 'rb'))"
+    "datasets = pickle.load(open('../data/jira-issues-test.pickle', 'rb'))"
    ]
   },
   {