From 4502cdb33a6433b047a492f3e9ae7ecf8d5a16c1 Mon Sep 17 00:00:00 2001
From: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Date: Fri, 20 Mar 2020 10:41:23 +0100
Subject: [PATCH 1/2] PERF: allow to skip validation/sanitization in
 DataFrame._from_arrays

---
 pandas/core/frame.py                  | 36 +++++++++++++++++++++++++--
 pandas/core/internals/construction.py | 21 +++++++++-------
 2 files changed, 46 insertions(+), 11 deletions(-)

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index b9e43b1cd9b05..8fc3e5fb089dd 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -1889,8 +1889,40 @@ def to_records(
         return np.rec.fromarrays(arrays, dtype={"names": names, "formats": formats})
 
     @classmethod
-    def _from_arrays(cls, arrays, columns, index, dtype=None) -> "DataFrame":
-        mgr = arrays_to_mgr(arrays, columns, index, columns, dtype=dtype)
+    def _from_arrays(
+        cls, arrays, columns, index, dtype=None, verify_integrity=True
+    ) -> "DataFrame":
+        """
+        Create DataFrame from a list of arrays corresponding to the columns.
+
+        Parameters
+        ----------
+        arrays : list-like of arrays
+            Each array in the list corresponds to one column, in order.
+        columns : list-like, Index
+            The column names for the resulting DataFrame.
+        index : list-like, Index
+            The rows labels for the resulting DataFrame.
+        dtype : dtype, optional
+            Optional dtype to enforce for all arrays.
+        verify_integrity : bool, default True
+            Validate and homogenize all input. If set to False, it is assumed
+            that all elements of `arrays` are actual arrays to be stored in
+            a block, have the same length as and are aligned with the index,
+            and that `columns` and `index` are ensured to be an Index object.
+
+        Returns
+        -------
+        DataFrame
+        """
+        mgr = arrays_to_mgr(
+            arrays,
+            columns,
+            index,
+            columns,
+            dtype=dtype,
+            verify_integrity=verify_integrity,
+        )
         return cls(mgr)
 
     @deprecate_kwarg(old_arg_name="fname", new_arg_name="path")
diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py
index c4416472d451c..3e0fb8455884a 100644
--- a/pandas/core/internals/construction.py
+++ b/pandas/core/internals/construction.py
@@ -53,23 +53,26 @@
 # BlockManager Interface
 
 
-def arrays_to_mgr(arrays, arr_names, index, columns, dtype=None):
+def arrays_to_mgr(arrays, arr_names, index, columns, dtype=None, verify_integrity=True):
     """
     Segregate Series based on type and coerce into matrices.
 
     Needs to handle a lot of exceptional cases.
     """
-    # figure out the index, if necessary
-    if index is None:
-        index = extract_index(arrays)
-    else:
-        index = ensure_index(index)
+    if verify_integrity:
+        # figure out the index, if necessary
+        if index is None:
+            index = extract_index(arrays)
+        else:
+            index = ensure_index(index)
 
-    # don't force copy because getting jammed in an ndarray anyway
-    arrays = _homogenize(arrays, index, dtype)
+        # don't force copy because getting jammed in an ndarray anyway
+        arrays = _homogenize(arrays, index, dtype)
+
+        columns = ensure_index(columns)
 
     # from BlockManager perspective
-    axes = [ensure_index(columns), index]
+    axes = [columns, index]
 
     return create_block_manager_from_arrays(arrays, arr_names, axes)
 

From a0d1c2769b08f1274f2c6d29bc8fece8bde0e538 Mon Sep 17 00:00:00 2001
From: Joris Van den Bossche <jorisvandenbossche@gmail.com>
Date: Fri, 20 Mar 2020 11:17:54 +0100
Subject: [PATCH 2/2] clarify array type

---
 pandas/core/frame.py | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 8fc3e5fb089dd..d1ba85c50d91d 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -1907,9 +1907,10 @@ def _from_arrays(
             Optional dtype to enforce for all arrays.
         verify_integrity : bool, default True
             Validate and homogenize all input. If set to False, it is assumed
-            that all elements of `arrays` are actual arrays to be stored in
-            a block, have the same length as and are aligned with the index,
-            and that `columns` and `index` are ensured to be an Index object.
+            that all elements of `arrays` are actual arrays how they will be
+            stored in a block (numpy ndarray or ExtensionArray), have the same
+            length as and are aligned with the index, and that `columns` and
+            `index` are ensured to be an Index object.
 
         Returns
         -------