diff options
Diffstat (limited to 'Fundamentals_of_Accelerated_Data_Science')
5 files changed, 38 insertions, 10 deletions
diff --git a/Fundamentals_of_Accelerated_Data_Science/1-08_cudf-polars.ipynb b/Fundamentals_of_Accelerated_Data_Science/1-08_cudf-polars.ipynb index c0f1115..6f810c8 100644 --- a/Fundamentals_of_Accelerated_Data_Science/1-08_cudf-polars.ipynb +++ b/Fundamentals_of_Accelerated_Data_Science/1-08_cudf-polars.ipynb @@ -803,7 +803,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "id": "6f5883f3-6238-4f98-970b-f06adabfb50e", "metadata": {}, "outputs": [ @@ -846,7 +846,10 @@ ], "source": [ "# Show optimized Graph\n", - "lazy_result.show_graph(optimized=True)" + "lazy_result.show_graph(optimized=True)\n", + "\n", + "# pi - projection compute and keep these columns\n", + "# sigme - selection " ] }, { diff --git a/Fundamentals_of_Accelerated_Data_Science/2-04_networkx_cugraph.ipynb b/Fundamentals_of_Accelerated_Data_Science/2-04_networkx_cugraph.ipynb index 48764b4..e6f3382 100644 --- a/Fundamentals_of_Accelerated_Data_Science/2-04_networkx_cugraph.ipynb +++ b/Fundamentals_of_Accelerated_Data_Science/2-04_networkx_cugraph.ipynb @@ -62,6 +62,19 @@ ] }, { + "cell_type": "code", + "execution_count": null, + "id": "7375dbf9", + "metadata": {}, + "outputs": [], + "source": [ + "# https://networkx.org/documentation/stable/reference/configs.html\n", + "\n", + "# nx.config.backend_priority = [\"cugraph\", \"..\"]\n", + "# env NETWORKX_BACKEND_PRIORITY=\"cugraph,..\"" + ] + }, + { "cell_type": "markdown", "id": "697ea4c9-b416-43d5-9d2c-28aa41ef2561", "metadata": {}, @@ -291,12 +304,14 @@ "### Pagerank Centrality ###\n", "Determines a node's importance based on the quantity and quality of links to it, similar to Google's original PageRank algorithm\n", "\n", - "PageRank’s main difference from EigenCentrality is that it accounts for link direction. Each node in a network is assigned a score based on its number of incoming links (its ‘indegree’). These links are also weighted depending on the relative score of its originating node." + "PageRank’s main difference from EigenCentrality is that it accounts for link direction. Each node in a network is assigned a score based on its number of incoming links (its ‘indegree’). These links are also weighted depending on the relative score of its originating node.\n", + "\n", + "1/n" ] }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "id": "a17ee15b-8758-484b-82b9-a158187231c5", "metadata": {}, "outputs": [], diff --git a/Fundamentals_of_Accelerated_Data_Science/3-04_logistic_regression.ipynb b/Fundamentals_of_Accelerated_Data_Science/3-04_logistic_regression.ipynb index 3890ea7..4e4b2ab 100644 --- a/Fundamentals_of_Accelerated_Data_Science/3-04_logistic_regression.ipynb +++ b/Fundamentals_of_Accelerated_Data_Science/3-04_logistic_regression.ipynb @@ -205,7 +205,9 @@ "## Logistic Regression ##\n", "Logistic regression can be used to estimate the probability of an outcome as a function of some (assumed independent) inputs. In our case, we would like to estimate infection risk based on population members' age and sex.\n", "\n", - "Below we train a logistic regresion model. We first create a cuML logistic regression instance `logreg`. The `logreg.fit` method takes 2 arguments: the model's independent variables *X*, and the dependent variable *y*. Fit the `logreg` model using the `gdf` columns `age` and `sex` as *X* and the `infected` column as *y*." + "Below we train a logistic regresion model. We first create a cuML logistic regression instance `logreg`. The `logreg.fit` method takes 2 arguments: the model's independent variables *X*, and the dependent variable *y*. Fit the `logreg` model using the `gdf` columns `age` and `sex` as *X* and the `infected` column as *y*.\n", + "\n", + "1/(1+e^{-z}) sigmoid" ] }, { @@ -637,6 +639,13 @@ ] }, { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { "cell_type": "markdown", "metadata": {}, "source": [ diff --git a/Fundamentals_of_Accelerated_Data_Science/3-06_xgboost.ipynb b/Fundamentals_of_Accelerated_Data_Science/3-06_xgboost.ipynb index 654a782..d3548f2 100644 --- a/Fundamentals_of_Accelerated_Data_Science/3-06_xgboost.ipynb +++ b/Fundamentals_of_Accelerated_Data_Science/3-06_xgboost.ipynb @@ -443,7 +443,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -453,8 +453,6 @@ " 'device': 'cuda',\n", " 'tree_method': 'hist',\n", " 'objective': 'binary:logistic',\n", - " 'grow_policy': 'lossguide',\n", - " 'eval_metric': 'logloss',\n", " 'subsample': '0.8'\n", "}" ] diff --git a/Fundamentals_of_Accelerated_Data_Science/3-07_triton.ipynb b/Fundamentals_of_Accelerated_Data_Science/3-07_triton.ipynb index 757b3fa..47d586c 100644 --- a/Fundamentals_of_Accelerated_Data_Science/3-07_triton.ipynb +++ b/Fundamentals_of_Accelerated_Data_Science/3-07_triton.ipynb @@ -120,11 +120,14 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": null, "id": "61d898fb-a8d2-4d1c-a13f-2c4be6c18969", "metadata": {}, "outputs": [], "source": [ + "# RAPIDS Forest Inference Library\n", + "# FIL returns class labels or probabilities\n", + "# mem / disk\n", "config_text = f\"\"\"backend: \"fil\"\n", "max_batch_size: 32768\n", "input [ \n", @@ -148,7 +151,7 @@ " value: {{ string_value: \"xgboost_json\" }}\n", " }},\n", " {{\n", - " key: \"output_class\"\n", + " key: \"output_class\" \n", " value: {{ string_value: \"false\" }}\n", " }},\n", " {{\n", |