uploaded results up to 7/9/20

PSLmodels · Jul 8, 2020 · 09ad628 · 09ad628
1 parent 240ccc1
commit 09ad628
Show file tree

Hide file tree

Showing 14 changed files with 37 additions and 141 deletions.
diff --git a/models/Sentence_based/stage_1_matrix_forecast.xlsx b/models/Sentence_based/stage_1_matrix_forecast.xlsx
diff --git a/models/Sentence_based/stage_1_matrix_test.xlsx b/models/Sentence_based/stage_1_matrix_test.xlsx
diff --git a/models/Sentence_based/stage_1_matrix_train.xlsx b/models/Sentence_based/stage_1_matrix_train.xlsx
diff --git a/models/Sentence_based/stage_2_results_forecast.xlsx b/models/Sentence_based/stage_2_results_forecast.xlsx
diff --git a/models/Sentence_based/stage_2_results_test.xlsx b/models/Sentence_based/stage_2_results_test.xlsx
diff --git a/models/Sentence_based/stage_2_results_train.xlsx b/models/Sentence_based/stage_2_results_train.xlsx
diff --git a/notebook/train_model.ipynb b/notebook/train_model.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -29,25 +29,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Raw data already present locally.\n",
-      "Finished processing data.\n",
-      "Uploaded processed data to s3.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model_settings = initialize_model_settings()\n",
     "\n",
     "\n",
-    "# get_raw_data(model_settings, \"s3\")\n",
-    "get_raw_data(model_settings, \"local\") ## If raw data already present locally\n",
+    "get_raw_data(model_settings, \"s3\")\n",
+    "# get_raw_data(model_settings, \"local\") ## If raw data already present locally\n",
     "\n",
     "process_data(model_settings)\n",
     "\n",
@@ -89,84 +79,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated train and test data.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\weifeng\\Anaconda3\\envs\\pci_pt\\lib\\site-packages\\torch\\nn\\parallel\\data_parallel.py:26: UserWarning: \n",
-      "    There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n",
-      "    has less than 75% of the memory or cores of GPU 0. You can do so by setting\n",
-      "    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n",
-      "    environment variable.\n",
-      "  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n",
-      "  0%|                                                                                          | 0/160 [00:00<?, ?it/s]"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Loaded the requested model\n",
-      "Forecast: \n",
-      "- # of obs: 154194\n",
-      "160 batches\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "161it [16:00,  5.97s/it]                                                                                               \n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Generated train and test data.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\weifeng\\Anaconda3\\envs\\pci_pt\\lib\\site-packages\\torch\\nn\\parallel\\data_parallel.py:26: UserWarning: \n",
-      "    There is an imbalance between your GPUs. You may want to exclude GPU 1 which\n",
-      "    has less than 75% of the memory or cores of GPU 0. You can do so by setting\n",
-      "    the device_ids argument to DataParallel, or by setting the CUDA_VISIBLE_DEVICES\n",
-      "    environment variable.\n",
-      "  warnings.warn(imbalance_warn.format(device_ids[min_pos], device_ids[max_pos]))\n",
-      "  0%|                                                                                          | 0/109 [00:00<?, ?it/s]"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Loaded the requested model\n",
-      "Forecast: \n",
-      "- # of obs: 105401\n",
-      "109 batches\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "110it [10:58,  5.99s/it]                                                                                               \n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "for stage in [1, 2]:\n",
     "\n",
@@ -177,11 +92,11 @@
     "    ## from_s3=True if model is not present locally\n",
     "    ## from_s3=False if model is present locally\n",
     "    \n",
-    "#     print(\"Training: \")\n",
-    "#     calc_results(model_settings, stage, model, device, df_train_unbal, \"train\")\n",
+    "    print(\"Training: \")\n",
+    "    calc_results(model_settings, stage, model, device, df_train_unbal, \"train\")\n",
     "    \n",
-    "#     print(\"Testing: \")\n",
-    "#     calc_results(model_settings, stage, model, device, df_test ,       \"test\")\n",
+    "    print(\"Testing: \")\n",
+    "    calc_results(model_settings, stage, model, device, df_test ,       \"test\")\n",
     "    \n",
     "    print(\"Forecast: \")\n",
     "    calc_results(model_settings, stage, model, device, df_forecast,    \"forecast\")\n"
@@ -204,7 +119,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.6.10"
   }
  },
  "nbformat": 4,

diff --git a/notebook/visualization.html b/notebook/visualization.html
diff --git a/notebook/visualization.rmd b/notebook/visualization.rmd
@@ -21,7 +21,7 @@ read_model_prediction = function(x){
 }
 
 version = "0.1.0"
-last_date = as.Date("2020-07-08")
+last_date = as.Date("2020-07-09")
 
 ```
 
@@ -234,9 +234,9 @@ foreach(x = results, j = names(results)) %do% {
 			legend.position = "bottom",
 			legend.background=element_blank(),
 			panel.grid.minor=element_blank(),
-			panel.grid.major=element_blank()
-			# axis.title.y.left = element_text(colour = "red"),
-			# axis.title.y.right = element_text(color = "blue")
+			panel.grid.major=element_blank(),
+			axis.title.y.left = element_text(colour = "blue"),
+			axis.title.y.right = element_text(color = "red")
 			) + 
 		guides(color = guide_legend(reverse = FALSE))
 

diff --git a/results/PCI-Outbreak_v0.1.0_2020-07-09.xlsx b/results/PCI-Outbreak_v0.1.0_2020-07-09.xlsx
diff --git a/results/pci-outbreak.png b/results/pci-outbreak.png
diff --git a/results/pci-outbreak_w_caption.png b/results/pci-outbreak_w_caption.png
diff --git a/src/header.r b/src/header.r
@@ -18,7 +18,7 @@ manage_packages = function() {
 	checkpoint::checkpoint(
 		checkpointLocation = "~/",
 		snapshotDate = "2020-05-25", 
-		R.version = "3.6.2"
+		R.version = "3.6.3"
 	)
 
 	## Import packages

diff --git a/src/model_settings.py b/src/model_settings.py
@@ -3,7 +3,7 @@
 
 def initialize_model_settings():
 
-    last_date = pd.Timestamp(2020,7,8)
+    last_date = pd.Timestamp(2020,7,9)
 
     model_settings = {
 
@@ -30,7 +30,7 @@ def initialize_model_settings():
 
     'max_length'            : 100,
     'batch_size'            : 24,
-    'predict_batch_size'    : 960,
+    'predict_batch_size'    : 1280,
     'epochs'                : 20,
     'cuda_index'            : 0,
     'multi_gpu'             : True,