Add init_spark_standalone for local node (intel-analytics#2685)

* initial version

* remove

* update to local

* remove

* style

* fix path

* fix

* update pythonhome

python/orca/src/bigdl/orca/data/shard.py

@@ -301,7 +301,7 @@ def to_ray(self):
         def put_to_plasma(ids):
             def f(index, iterator):
                 import pyarrow.plasma as plasma
-                from zoo.orca.data.utils import get_node_ip
+                from zoo.util.utils import get_node_ip
                 res = list(iterator)
                 client = plasma.connect(object_store_address)
                 target_id = ids[index]

python/orca/src/bigdl/orca/data/utils.py

@@ -237,33 +237,6 @@ def get_class_name(obj):
     return obj.__class__.__name__
 
 
-def get_node_ip():
-    """
-    This function is ported from ray to get the ip of the current node. In the settings where
-    Ray is not involved, calling ray.services.get_node_ip_address would introduce Ray overhead.
-    """
-    import socket
-    import errno
-    s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
-    try:
-        # This command will raise an exception if there is no internet connection.
-        s.connect(("8.8.8.8", 80))
-        node_ip_address = s.getsockname()[0]
-    except OSError as e:
-        node_ip_address = "127.0.0.1"
-        # [Errno 101] Network is unreachable
-        if e.errno == errno.ENETUNREACH:
-            try:
-                # try get node ip address from host name
-                host_name = socket.getfqdn(socket.gethostname())
-                node_ip_address = socket.gethostbyname(host_name)
-            except Exception:
-                pass
-    finally:
-        s.close()
-    return node_ip_address
-
-
 def _convert_list_tuple(data, allow_tuple, allow_list):
     if not allow_list and not allow_tuple:
         raise ValueError("value of x and y should be a ndarray, but get a " +