From b5af6f1cd554b57504554056fd6a239e8da4244c Mon Sep 17 00:00:00 2001
From: Jon Seddon <jon.seddon@metoffice.gov.uk>
Date: Mon, 20 Jul 2020 17:26:29 +0100
Subject: [PATCH] Look at number of requests uploaded

---
 .gitignore |  1 +
 d9_6.ipynb | 39 ++++++++++++++++++++++++++++++++-------
 2 files changed, 33 insertions(+), 7 deletions(-)
 create mode 100644 .gitignore

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..763513e
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.ipynb_checkpoints
diff --git a/d9_6.ipynb b/d9_6.ipynb
index a27363a..9c0e1fc 100644
--- a/d9_6.ipynb
+++ b/d9_6.ipynb
@@ -85,12 +85,10 @@
     "    institute__short_name__in=['MOHC', 'NERC'],\n",
     "    experiment__short_name__in=expts,\n",
     "    rip_code__in=mohc_stream2_members,\n",
-    "    datafile__isnull=False\n",
     "))\n",
     "\n",
     "others = DataRequest.objects.filter(\n",
     "    experiment__short_name__in=expts,\n",
-    "    datafile__isnull=False\n",
     ").exclude(\n",
     "    # Exclude MOHC Stream 2\n",
     "    institute__short_name__in=['MOHC', 'NERC'],\n",
@@ -102,7 +100,7 @@
     "    rip_code='r1i1p1f1'\n",
     ").distinct()\n",
     "\n",
-    "stream_1_2 = hadgem_s2 | others"
+    "stream_1_2 = (hadgem_s2 | others).filter(datafile__isnull=False)"
    ]
   },
   {
@@ -131,7 +129,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "30955 data requests were uploaded consisting of 1.5 PB\n"
+      "31048 data requests were uploaded consisting of 1.5 PB\n"
      ]
     }
    ],
@@ -175,8 +173,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "5941 unique data requests were restored, 19.2% of the total uploaded\n",
-      "417.6 TB of unique data requests were restored, 26.5% of the volume uploaded\n"
+      "6070 unique data requests were restored, 19.6% of the total uploaded\n",
+      "426.3 TB of unique data requests were restored, 27.3% of the volume uploaded\n"
      ]
     }
    ],
@@ -187,6 +185,33 @@
     "      f'were restored, '\n",
     "      f'{volume_stream_1_2_restored / volume_stream_1_2:.1%} of the volume uploaded')"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Find planned Stream 1 and 2 (ignore additional HadGEM)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "60275 data requests were originally planned to be uploaded. 31048 data requests were actually uploaded, which is 51.5% of the number planned\n"
+     ]
+    }
+   ],
+   "source": [
+    "stream_1_2_planned = hadgem_s2 | others\n",
+    "print(f'{stream_1_2_planned.count()} data requests were originally planned to be uploaded. '\n",
+    "      f'{stream_1_2.count()} data requests were actually uploaded, which is '\n",
+    "      f'{stream_1_2.count() / stream_1_2_planned.count():.1%} of the number planned')"
+   ]
   }
  ],
  "metadata": {
@@ -205,7 +230,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.8"
+   "version": "3.6.7"
   }
  },
  "nbformat": 4,