From ecff26aedf328622c93ffb231af95f9c84637338 Mon Sep 17 00:00:00 2001
From: Serg Gini <kornburn@gmail.com>
Date: Sat, 29 Jul 2023 04:05:15 +0400
Subject: [PATCH 1/3] Implemented tutorial for Clang
---
apply_model/README.md | 6 +
apply_model/clang/readme.md | 14 ++
apply_model/clang/src/main.c | 180 ++++++++++++++
apply_model/clang/train_model.ipynb | 373 ++++++++++++++++++++++++++++
apply_model/dlang/readme.md | 7 +
apply_model/dlang/src/main.d | 176 +++++++++++++
apply_model/dlang/train_model.ipynb | 373 ++++++++++++++++++++++++++++
7 files changed, 1129 insertions(+)
create mode 100644 apply_model/clang/readme.md
create mode 100644 apply_model/clang/src/main.c
create mode 100644 apply_model/clang/train_model.ipynb
create mode 100644 apply_model/dlang/readme.md
create mode 100644 apply_model/dlang/src/main.d
create mode 100644 apply_model/dlang/train_model.ipynb
diff --git a/apply_model/README.md b/apply_model/README.md
index 00a098d..5ce90d5 100644
--- a/apply_model/README.md
+++ b/apply_model/README.md
@@ -14,3 +14,9 @@
* [Apply CatBoost model from Rust](./rust/train_model.ipynb)
* Explore how to apply CatBoost model from Rust application. If you just want to look at code snippets you can go directly to [main.rs](./rust/src/main.rs)
+
+* [Apply CatBoost model from C](./clang/train_model.ipynb)
+ * Explore how to apply CatBoost model from C application. If you just want to look at code snippets you can go directly to [main.c](./clang/src/main.c)
+
+* [Apply CatBoost model from D](./dlang/train_model.ipynb)
+ * Explore how to apply CatBoost model from D application. If you just want to look at code snippets you can go directly to [main.d](./dlang/src/main.d)
diff --git a/apply_model/clang/readme.md b/apply_model/clang/readme.md
new file mode 100644
index 0000000..13b54a5
--- /dev/null
+++ b/apply_model/clang/readme.md
@@ -0,0 +1,14 @@
+# Apply CatBoost model from C
+This tutorial consists of two parts:
+- first part where we preprocess dataset and train the classifier model.
+ This part can be found in [train_model.ipynb](train_model.ipynb).
+- second part where we load model into C application and then apply it.
+ This part presented as a C file. At first you need to build a library, as it is suggested on [](https://catboost.ai/en/docs/concepts/c-plus-plus-api_dynamic-c-pluplus-wrapper). To run, you can execute:
+ * in case Linux/macOS
+
+ `clang <your sources and options> -L<path_to_dir_with_libcatboostmodel> -lcatboostmodel`
+ * in case Windows
+
+ `cl.exe <your sources and options> /link <path_to_dir_with_libcatboostmodel>\catboostmodel.lib`
+
+ If you just want to look at code snippets you can go directly to [src/main.c](src/main.c).
diff --git a/apply_model/clang/src/main.c b/apply_model/clang/src/main.c
new file mode 100644
index 0000000..56c4cb2
--- /dev/null
+++ b/apply_model/clang/src/main.c
@@ -0,0 +1,180 @@
+#include <stdio.h>
+#include <math.h>
+
+// Bring catboost module into the scope
+#include <path_to_dir_with_header_file/c_api.h>
+
+double sigmoid(double x) {
+ return 1. / (1. + exp(-x));
+}
+
+char* answer(bool makes_over_50k_a_year) {
+ if (makes_over_50k_a_year) {
+ return "makes over 50k a year";
+ } else {
+ return "doesn't make over 50k a year";
+ }
+}
+
+int main(int argc, const char * argv[]) {
+ // Load "adult.cbm" model that we trained withing Jupyter Notebook
+ ModelCalcerHandle* modelHandle;
+ modelHandle = ModelCalcerCreate();
+ if (!LoadFullModelFromFile(modelHandle, "adult.cbm")) {
+ printf("LoadFullModelFromFile error message: %s\n", GetErrorString());
+ }
+
+ // You can also try to load your own model just replace "adult.cbm" with path to your model that classifies data
+ // from UCI Adult Dataset.
+
+ printf("Adult dataset model metainformation\n");
+
+ printf("tree count: %zu\n", GetTreeCount(modelHandle));
+
+ // In our case we were solving a binary classification problem (weather person makes over 50K a year), so the
+ // dimension of the prediction will be 1, it will return probability of the object to belong to the positive
+ // class; in our case we had two classed encoded as "<=50K" and ">50K", during data preprocessing (see
+ // `get_fixed_adult()` in Notebook) we encoded "<=50K" as 0 and ">50K" as 1, so that ">50K" became a positive
+ // class. Probability of the negative class ("<=50K") can be easily deduced as (1-p) where p is a probability of
+ // positive class.
+ //
+ // For most of cases prediction dimension will be 1 (for regression and for ranking), it can be N for cases of
+ // multiclassification, where N is a number of classes.
+ printf("prediction dimension: %zu\n", GetDimensionsCount(modelHandle));
+
+ printf("numeric feature count: %zu\n", GetFloatFeaturesCount(modelHandle));
+
+ printf("categoric feature count: %zu\n", GetCatFeaturesCount(modelHandle));
+
+ // Ok now lets try to use our model for prediction. We'll look at the test part of Adult dataset. You will need
+ // to download it [1] from UCI repository. Look for "adult.test", "adult.name" will also be useful because it
+ // in contains human-readable description of the dataset.
+ //
+ // So the first line of test part of the dataset is:
+ //
+ // "25, Private, 226802, 11th, 7, Never-married, Machine-op-inspct, Own-child, Black, Male, 0, 0, 40, United-States, <=50K."
+ //
+ // Based on "adult.name" we can recover its vectors of numeric and categoric features (in our case all
+ // "continuous" features are numeric and all other features are categoric):
+ //
+ // numericFeatures: {25, 226802, 7, 0, 0, 40}
+ // categoricFeatures: {"Private", "11th", "Never-married", "Machine-op-inspct", "Own-child", "Black", "Male", "United-States"}
+ //
+ // And he doesn't make 50K per year. Also note that order of numeric and categoric features in source data and
+ // in `numericFeatures` and `categoricFeatures` is kept the same. Otherwise we can't apply the model (well, we
+ // can, but result of prediction will be garbage).
+ //
+ // Now lets run it! And let's call this person "person A", to make variable names unique.
+ //
+ // [1]: https://archive.ics.uci.edu/ml/machine-learning-databases/adult/
+
+ printf("\n");
+
+ float pers_a_num_feat[6] = {25., 226802., 7., 0., 0., 40.};
+ char* pers_a_cat_feat[8] = {"Private","11th","Never-married","Machine-op-inspct","Own-child","Black","Male","United-States"};
+
+ double result_a[1];
+
+ const float* a_num_feat_ptr = pers_a_num_feat;
+ const char** a_cat_feat_ptr = pers_a_cat_feat;
+
+ if (!CalcModelPrediction(
+ modelHandle,
+ 1,
+ &a_num_feat_ptr, 6,
+ &a_cat_feat_ptr, 8,
+ &result_a, 1)
+ ) {
+ printf("CalcModelPrediction error message: %s\n", GetErrorString());
+ }
+
+ // Since we made prediction only for one person and prediction dimension is 1, proability of person A make
+ // over 50K will have index 0 in `person_a_prediction`.
+ //
+ // CatBoost doesn't compute "probability", to turn CatBoost prediction into a probability we'll need to apply
+ // sigmoid function.
+ double pers_a_makes_over_50k_prob = sigmoid(result_a[0]);
+ printf("Person A make over 50K a year with probability %f\n", pers_a_makes_over_50k_prob);
+
+ // When we were training CatBoost we used a default classification threshold for AUC which is equal to 0.5,
+ // this means that our formula is optimized for this threashold, though we may change threshold to optimize some
+ // other metric on a different dataset, but we won't do it in this tutorial.
+ double classification_threshold = 0.5;
+
+ bool pers_a_makes_over_50k = pers_a_makes_over_50k_prob > classification_threshold;
+ printf("Person A %s\n", answer(pers_a_makes_over_50k));
+
+ // Now lets find an example with missing features and income greater than 50K a year. At line 40 of "adult.test"
+ // we can find following line:
+ //
+ // "40, Private, 85019, Doctorate, 16, Married-civ-spouse, Prof-specialty, Husband, Asian-Pac-Islander, Male, 0, 0, 45, ?, >50K."
+ //
+ // Lets call this person "Person B", dataset missing (missing features are marked with "?") "native-county"
+ // feature for Person B. When we were doing preprocessing in `get_fixed_adult` we replaced missing categoric
+ // features with string "nan", now, when we apply trained model we must also use "nan" for missing features.
+ // Lets write out feature vectors for Person B:
+ //
+ // numericFeatures = {40, 85019, 16, 0, 0, 45};
+ // categoricFeatures = {"Private", "Doctorate", "Married-civ-spouce", "Prof-specialty", "Husband", "Asian-Pac-Islander", "Male", "nan"};
+ //
+ // And according to the dataset Person B makes more than 50K a year. Ok, lets try to apply the model to this
+ // example.
+
+ printf("\n");
+
+ float pers_b_num_feat[w] = {40., 85019., 16., 0., 0., 45.};
+ char* pers_b_cat_feat[8] = {"Private","Doctorate","Married-civ-spouce","Prof-specialty","Husband","Asian-Pac-Islander","Male","nan"};
+
+ double result_b[1];
+
+ const float* b_num_feat_ptr = pers_b_num_feat;
+ const char** b_cat_feat_ptr = pers_b_cat_feat;
+
+ if (!CalcModelPrediction(
+ modelHandle,
+ 1,
+ &b_num_feat_ptr, 6,
+ &b_cat_feat_ptr, 8,
+ &result_b, 1)
+ ) {
+ printf("CalcModelPrediction error message: %s\n", GetErrorString());
+ }
+ double pers_b_makes_over_50k_prob = sigmoid(result_b[0]);
+ bool pers_b_makes_over_50k = pers_b_makes_over_50k_prob > classification_threshold;
+ printf("Person B make over 50K a year with probability %f\n", pers_b_makes_over_50k_prob);
+ printf("Person B %s\n", answer(pers_b_makes_over_50k));
+
+ // Let's try to apply the model to Person A and Person B in one call.
+ printf("\n");
+
+ float* pers_ab_num_feat[2] = {pers_a_num_feat, pers_b_num_feat};
+ char** pers_ab_cat_feat[2] = {pers_a_cat_feat, pers_b_cat_feat};
+
+ double result_ab[2];
+
+ const float** ab_num_feat_ptr = (const float**)pers_ab_num_feat;
+ const char*** ab_cat_feat_ptr = (const char**)pers_ab_cat_feat;
+
+ if (!CalcModelPrediction(
+ modelHandle,
+ 2,
+ ab_num_feat_ptr, 6,
+ ab_cat_feat_ptr, 8,
+ &result_ab, 2)
+ ) {
+ printf("CalcModelPrediction error message: %s\n", GetErrorString());
+ }
+ double pers_ab_makes_over_50k_prob[2] = {sigmoid(result_ab[0]), sigmoid(result_ab[1])};
+ bool pers_ab_makes_over_50k[2] = {pers_ab_makes_over_50k_prob[0] > classification_threshold, pers_ab_makes_over_50k_prob[1] > classification_threshold};
+
+ printf("Using batch interface\n");
+
+ // Predictions should be same as above
+ printf("Person A make over 50K a year with probability %f\n", pers_ab_makes_over_50k_prob[0]);
+ printf("Person A %s\n", answer(pers_ab_makes_over_50k[0]));
+ printf("Person B make over 50K a year with probability %f\n", pers_ab_makes_over_50k_prob[1]);
+ printf("Person B %s\n", answer(pers_ab_makes_over_50k[1]));
+
+ ModelCalcerDelete(modelHandle);
+ return 0;
+}
\ No newline at end of file
diff --git a/apply_model/clang/train_model.ipynb b/apply_model/clang/train_model.ipynb
new file mode 100644
index 0000000..0d03029
--- /dev/null
+++ b/apply_model/clang/train_model.ipynb
@@ -0,0 +1,373 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# catboost for clang tutorial"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -q numpy pandas catboost"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from __future__ import absolute_import, division, print_function, unicode_literals"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "CatBoost version 0.14.2\n",
+ "NumPy version 1.16.3\n",
+ "Pandas version 0.24.2\n"
+ ]
+ }
+ ],
+ "source": [
+ "import catboost as cb\n",
+ "import catboost.datasets as cbd\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "\n",
+ "# print module versions for reproducibility\n",
+ "print('CatBoost version {}'.format(cb.__version__))\n",
+ "print('NumPy version {}'.format(np.__version__))\n",
+ "print('Pandas version {}'.format(pd.__version__))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ " Download \"Adult Data Set\" [1] from UCI Machine Learning Repository.\n",
+ "\n",
+ " Will return two pandas.DataFrame-s, first with train part (adult.data) and second with test part\n",
+ " (adult.test) of the dataset.\n",
+ "\n",
+ " [1]: https://archive.ics.uci.edu/ml/datasets/Adult\n",
+ " \n"
+ ]
+ }
+ ],
+ "source": [
+ "# We are going to use UCI Adult Data Set because it has both numerical and categorical \n",
+ "# features and also has missing features.\n",
+ "print(cbd.adult.__doc__)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_fixed_adult():\n",
+ " train, test = cbd.adult()\n",
+ " \n",
+ " # CatBoost doesn't support pandas.DataFrame missing values for categorical features out \n",
+ " # of the box (seed issue #571 on GitHub or issue MLTOOLS-2785 in internal tracker). So \n",
+ " # we have to replace them with some designated string manually. \n",
+ " for dataset in (train, test, ):\n",
+ " for name in (name for name, dtype in dict(dataset.dtypes).items() if dtype == np.object):\n",
+ " dataset[name].fillna('nan', inplace=True)\n",
+ " \n",
+ " X_train, y_train = train.drop('income', axis=1), train.income\n",
+ " X_test, y_test = test.drop('income', axis=1), test.income\n",
+ " return X_train, y_train, X_test, y_test"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train, y_train, _, _ = get_fixed_adult()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>age</th>\n",
+ " <th>workclass</th>\n",
+ " <th>fnlwgt</th>\n",
+ " <th>education</th>\n",
+ " <th>education-num</th>\n",
+ " <th>marital-status</th>\n",
+ " <th>occupation</th>\n",
+ " <th>relationship</th>\n",
+ " <th>race</th>\n",
+ " <th>sex</th>\n",
+ " <th>capital-gain</th>\n",
+ " <th>capital-loss</th>\n",
+ " <th>hours-per-week</th>\n",
+ " <th>native-country</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>39.0</td>\n",
+ " <td>State-gov</td>\n",
+ " <td>77516.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Never-married</td>\n",
+ " <td>Adm-clerical</td>\n",
+ " <td>Not-in-family</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>2174.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>50.0</td>\n",
+ " <td>Self-emp-not-inc</td>\n",
+ " <td>83311.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Exec-managerial</td>\n",
+ " <td>Husband</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>13.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>38.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>215646.0</td>\n",
+ " <td>HS-grad</td>\n",
+ " <td>9.0</td>\n",
+ " <td>Divorced</td>\n",
+ " <td>Handlers-cleaners</td>\n",
+ " <td>Not-in-family</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>53.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>234721.0</td>\n",
+ " <td>11th</td>\n",
+ " <td>7.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Handlers-cleaners</td>\n",
+ " <td>Husband</td>\n",
+ " <td>Black</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>28.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>338409.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Prof-specialty</td>\n",
+ " <td>Wife</td>\n",
+ " <td>Black</td>\n",
+ " <td>Female</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>Cuba</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " age workclass fnlwgt education education-num \\\n",
+ "0 39.0 State-gov 77516.0 Bachelors 13.0 \n",
+ "1 50.0 Self-emp-not-inc 83311.0 Bachelors 13.0 \n",
+ "2 38.0 Private 215646.0 HS-grad 9.0 \n",
+ "3 53.0 Private 234721.0 11th 7.0 \n",
+ "4 28.0 Private 338409.0 Bachelors 13.0 \n",
+ "\n",
+ " marital-status occupation relationship race sex \\\n",
+ "0 Never-married Adm-clerical Not-in-family White Male \n",
+ "1 Married-civ-spouse Exec-managerial Husband White Male \n",
+ "2 Divorced Handlers-cleaners Not-in-family White Male \n",
+ "3 Married-civ-spouse Handlers-cleaners Husband Black Male \n",
+ "4 Married-civ-spouse Prof-specialty Wife Black Female \n",
+ "\n",
+ " capital-gain capital-loss hours-per-week native-country \n",
+ "0 2174.0 0.0 40.0 United-States \n",
+ "1 0.0 0.0 13.0 United-States \n",
+ "2 0.0 0.0 40.0 United-States \n",
+ "3 0.0 0.0 40.0 United-States \n",
+ "4 0.0 0.0 40.0 Cuba "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_train.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Warning: Custom metrics will not be evaluated because there are no test datasets\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "<catboost.core.CatBoostClassifier at 0x7fe0d1ac77f0>"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# If you want to find out how we found these parameters check \"Simple classification \n",
+ "# example with missing feature handling and parameter tuning\" tutorial in `classification`\n",
+ "# subdirectory of tutorials\n",
+ "model = cb.CatBoostClassifier(\n",
+ " class_names=('<=50K', '>50K'),\n",
+ " loss_function='Logloss',\n",
+ " eval_metric='AUC', \n",
+ " custom_metric=['AUC'],\n",
+ " iterations=100,\n",
+ " random_seed=20181224,\n",
+ " learning_rate=0.4234185321620083, \n",
+ " depth=5, \n",
+ " l2_leaf_reg=9.464266235679002)\n",
+ "model.fit(\n",
+ " cb.Pool(X_train, y_train, cat_features=np.where(X_train.dtypes != np.float)[0]),\n",
+ " verbose=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model.save_model('adult.cbm')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "156K\tadult.cbm\r\n"
+ ]
+ }
+ ],
+ "source": [
+ "!du -sh adult.cbm"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We got the model, now it's time to use it via `catboost` package for C. Next part of the tutorial\n",
+ "will be in a C project."
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/apply_model/dlang/readme.md b/apply_model/dlang/readme.md
new file mode 100644
index 0000000..61cbd0c
--- /dev/null
+++ b/apply_model/dlang/readme.md
@@ -0,0 +1,7 @@
+# Apply CatBoost model from Rust
+This tutorial consists of two parts:
+- first part where we preprocess dataset and train the classifier model.
+ This part can be found in [train_model.ipynb](train_model.ipynb).
+- second part where we load model into Rust application and then apply it.
+ This part presented as a small Cargo project. To run, execute `cargo run --release`.
+ If you just want to look at code snippets you can go directly to [src/main.rs](src/main.rs).
diff --git a/apply_model/dlang/src/main.d b/apply_model/dlang/src/main.d
new file mode 100644
index 0000000..8a9242a
--- /dev/null
+++ b/apply_model/dlang/src/main.d
@@ -0,0 +1,176 @@
+// Bring catboost module into the scope
+use catboost;
+
+fn sigmoid(x: f64) -> f64 {
+ 1. / (1. + (-x).exp())
+}
+
+fn answer(makes_over_50k_a_year: bool) -> &'static str {
+ if makes_over_50k_a_year {
+ "makes over 50K a year"
+ } else {
+ "doesn't make over 50K a year"
+ }
+}
+
+fn main() {
+ // Load "adult.cbm" model that we trained withing Jupyter Notebook
+ let model_path = "adult.cbm";
+ let model = catboost::Model::load(model_path).unwrap();
+
+ // You can also try to load your own model just replace "adult.cbm" with path to your model that classifies data
+ // from UCI Adult Dataset.
+
+ println!("Adult dataset model metainformation\n");
+
+ println!("tree count: {}", model.get_tree_count());
+
+ // In our case we were solving a binary classification problem (weather person makes over 50K a year), so the
+ // dimension of the prediction will be 1, it will return probability of the object to belong to the positive
+ // class; in our case we had two classed encoded as "<=50K" and ">50K", during data preprocessing (see
+ // `get_fixed_adult()` in Notebook) we encoded "<=50K" as 0 and ">50K" as 1, so that ">50K" became a positive
+ // class. Probability of the negative class ("<=50K") can be easily deduced as (1-p) where p is a probability of
+ // positive class.
+ //
+ // For most of cases prediction dimension will be 1 (for regression and for ranking), it can be N for cases of
+ // multiclassification, where N is a number of classes.
+ println!("prediction dimension: {}", model.get_dimensions_count());
+
+ println!("numeric feature count: {}", model.get_float_features_count());
+
+ println!("categoric feature count: {}", model.get_cat_features_count());
+
+ // Ok now lets try to use our model for prediction. We'll look at the test part of Adult dataset. You will need
+ // to download it [1] from UCI repository. Look for "adult.test", "adult.name" will also be useful because it
+ // in contains human-readable description of the dataset.
+ //
+ // So the first line of test part of the dataset is:
+ //
+ // "25, Private, 226802, 11th, 7, Never-married, Machine-op-inspct, Own-child, Black, Male, 0, 0, 40, United-States, <=50K."
+ //
+ // Based on "adult.name" we can recover its vectors of numeric and categoric features (in our case all
+ // "continuous" features are numeric and all other features are categoric):
+ //
+ // numericFeatures: {25, 226802, 7, 0, 0, 40}
+ // categoricFeatures: {"Private", "11th", "Never-married", "Machine-op-inspct", "Own-child", "Black", "Male", "United-States"}
+ //
+ // And he doesn't make 50K per year. Also note that order of numeric and categoric features in source data and
+ // in `numericFeatures` and `categoricFeatures` is kept the same. Otherwise we can't apply the model (well, we
+ // can, but result of prediction will be garbage).
+ //
+ // Now lets run it! And let's call this person "person A", to make variable names unique.
+ //
+ // [1]: https://archive.ics.uci.edu/ml/machine-learning-databases/adult/
+
+ println!();
+
+ let person_a_numeric_features = vec![25., 226_802., 7., 0., 0., 40.];
+ let person_a_categoric_features = vec![
+ String::from("Private"),
+ String::from("11th"),
+ String::from("Never-married"),
+ String::from("Machine-op-inspct"),
+ String::from("Own-child"),
+ String::from("Black"),
+ String::from("Male"),
+ String::from("United-States"),
+ ];
+ let person_a_prediction = model
+ .calc_model_prediction(
+ vec![person_a_numeric_features.clone()],
+ vec![person_a_categoric_features.clone()],
+ )
+ .unwrap();
+
+ // Since we made prediction only for one person and prediction dimension is 1, proability of person A make
+ // over 50K will have index 0 in `person_a_prediction`.
+ //
+ // CatBoost doesn't compute "probability", to turn CatBoost prediction into a probability we'll need to apply
+ // sigmoid function.
+ let person_a_makes_over_50k_probability = sigmoid(person_a_prediction[0]);
+ println!(
+ "Person A make over 50K a year with probability {}",
+ person_a_makes_over_50k_probability
+ );
+
+ // When we were training CatBoost we used a default classification threshold for AUC which is equal to 0.5,
+ // this means that our formula is optimized for this threashold, though we may change threshold to optimize some
+ // other metric on a different dataset, but we won't do it in this tutorial.
+ let classification_threshold = 0.5;
+
+ let person_a_makes_over_50k = person_a_makes_over_50k_probability > classification_threshold;
+ println!("Person A {}", answer(person_a_makes_over_50k));
+
+ // Now lets find an example with missing features and income greater than 50K a year. At line 40 of "adult.test"
+ // we can find following line:
+ //
+ // "40, Private, 85019, Doctorate, 16, Married-civ-spouse, Prof-specialty, Husband, Asian-Pac-Islander, Male, 0, 0, 45, ?, >50K."
+ //
+ // Lets call this person "Person B", dataset missing (missing features are marked with "?") "native-county"
+ // feature for Person B. When we were doing preprocessing in `get_fixed_adult` we replaced missing categoric
+ // features with string "nan", now, when we apply trained model we must also use "nan" for missing features.
+ // Lets write out feature vectors for Person B:
+ //
+ // numericFeatures = {40, 85019, 16, 0, 0, 45};
+ // categoricFeatures = {"Private", "Doctorate", "Married-civ-spouce", "Prof-specialty", "Husband", "Asian-Pac-Islander", "Male", "nan"};
+ //
+ // And according to the dataset Person B makes more than 50K a year. Ok, lets try to apply the model to this
+ // example.
+
+ println!();
+
+ let person_b_numeric_features = vec![40., 85019., 16., 0., 0., 45.];
+ let person_b_categoric_features = vec![
+ String::from("Private"),
+ String::from("Doctorate"),
+ String::from("Married-civ-spouce"),
+ String::from("Prof-specialty"),
+ String::from("Husband"),
+ String::from("Asian-Pac-Islander"),
+ String::from("Male"),
+ String::from("nan"),
+ ];
+ let person_b_prediction = model
+ .calc_model_prediction(
+ vec![person_b_numeric_features.clone()],
+ vec![person_b_categoric_features.clone()],
+ )
+ .unwrap();
+ let person_b_makes_over_50k_probability = sigmoid(person_b_prediction[0]);
+ let person_b_makes_over_50k = person_b_makes_over_50k_probability > classification_threshold;
+ println!(
+ "Person B make over 50K a year with probability {}",
+ person_b_makes_over_50k_probability
+ );
+ println!("Person B {}", answer(person_b_makes_over_50k));
+
+ // Let's try to apply the model to Person A and Person B in one call.
+
+ println!();
+
+ let persons_ab_numberic_features = vec![person_a_numeric_features, person_b_numeric_features];
+ let persons_ab_categoric_features = vec![person_a_categoric_features, person_b_categoric_features];
+ let persons_ab_predictions = model
+ .calc_model_prediction(persons_ab_numberic_features, persons_ab_categoric_features)
+ .unwrap();
+ let persons_ab_make_over_50k_probabilities =
+ vec![sigmoid(persons_ab_predictions[0]), sigmoid(persons_ab_predictions[1])];
+ let persons_ab_make_over_50k = vec![
+ persons_ab_make_over_50k_probabilities[0] > classification_threshold,
+ persons_ab_make_over_50k_probabilities[1] > classification_threshold,
+ ];
+
+ println!("Using batch interface");
+
+ // Predictions should be same as above
+ println!(
+ "Person A make over 50K a year with probability {}",
+ persons_ab_make_over_50k_probabilities[0]
+ );
+ println!("Person A {}", answer(persons_ab_make_over_50k[0]));
+ println!(
+ "Person B make over 50K a year with probability {}",
+ persons_ab_make_over_50k_probabilities[1]
+ );
+ println!("Person B {}", answer(persons_ab_make_over_50k[1]));
+}
diff --git a/apply_model/dlang/train_model.ipynb b/apply_model/dlang/train_model.ipynb
new file mode 100644
index 0000000..5de4826
--- /dev/null
+++ b/apply_model/dlang/train_model.ipynb
@@ -0,0 +1,373 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# catboost for rust tutorial"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "!pip install -q numpy pandas catboost"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from __future__ import absolute_import, division, print_function, unicode_literals"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "CatBoost version 0.14.2\n",
+ "NumPy version 1.16.3\n",
+ "Pandas version 0.24.2\n"
+ ]
+ }
+ ],
+ "source": [
+ "import catboost as cb\n",
+ "import catboost.datasets as cbd\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "\n",
+ "# print module versions for reproducibility\n",
+ "print('CatBoost version {}'.format(cb.__version__))\n",
+ "print('NumPy version {}'.format(np.__version__))\n",
+ "print('Pandas version {}'.format(pd.__version__))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\n",
+ " Download \"Adult Data Set\" [1] from UCI Machine Learning Repository.\n",
+ "\n",
+ " Will return two pandas.DataFrame-s, first with train part (adult.data) and second with test part\n",
+ " (adult.test) of the dataset.\n",
+ "\n",
+ " [1]: https://archive.ics.uci.edu/ml/datasets/Adult\n",
+ " \n"
+ ]
+ }
+ ],
+ "source": [
+ "# We are going to use UCI Adult Data Set because it has both numerical and categorical \n",
+ "# features and also has missing features.\n",
+ "print(cbd.adult.__doc__)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_fixed_adult():\n",
+ " train, test = cbd.adult()\n",
+ " \n",
+ " # CatBoost doesn't support pandas.DataFrame missing values for categorical features out \n",
+ " # of the box (seed issue #571 on GitHub or issue MLTOOLS-2785 in internal tracker). So \n",
+ " # we have to replace them with some designated string manually. \n",
+ " for dataset in (train, test, ):\n",
+ " for name in (name for name, dtype in dict(dataset.dtypes).items() if dtype == np.object):\n",
+ " dataset[name].fillna('nan', inplace=True)\n",
+ " \n",
+ " X_train, y_train = train.drop('income', axis=1), train.income\n",
+ " X_test, y_test = test.drop('income', axis=1), test.income\n",
+ " return X_train, y_train, X_test, y_test"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "X_train, y_train, _, _ = get_fixed_adult()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>age</th>\n",
+ " <th>workclass</th>\n",
+ " <th>fnlwgt</th>\n",
+ " <th>education</th>\n",
+ " <th>education-num</th>\n",
+ " <th>marital-status</th>\n",
+ " <th>occupation</th>\n",
+ " <th>relationship</th>\n",
+ " <th>race</th>\n",
+ " <th>sex</th>\n",
+ " <th>capital-gain</th>\n",
+ " <th>capital-loss</th>\n",
+ " <th>hours-per-week</th>\n",
+ " <th>native-country</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>39.0</td>\n",
+ " <td>State-gov</td>\n",
+ " <td>77516.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Never-married</td>\n",
+ " <td>Adm-clerical</td>\n",
+ " <td>Not-in-family</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>2174.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>50.0</td>\n",
+ " <td>Self-emp-not-inc</td>\n",
+ " <td>83311.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Exec-managerial</td>\n",
+ " <td>Husband</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>13.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>38.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>215646.0</td>\n",
+ " <td>HS-grad</td>\n",
+ " <td>9.0</td>\n",
+ " <td>Divorced</td>\n",
+ " <td>Handlers-cleaners</td>\n",
+ " <td>Not-in-family</td>\n",
+ " <td>White</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>53.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>234721.0</td>\n",
+ " <td>11th</td>\n",
+ " <td>7.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Handlers-cleaners</td>\n",
+ " <td>Husband</td>\n",
+ " <td>Black</td>\n",
+ " <td>Male</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>United-States</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>28.0</td>\n",
+ " <td>Private</td>\n",
+ " <td>338409.0</td>\n",
+ " <td>Bachelors</td>\n",
+ " <td>13.0</td>\n",
+ " <td>Married-civ-spouse</td>\n",
+ " <td>Prof-specialty</td>\n",
+ " <td>Wife</td>\n",
+ " <td>Black</td>\n",
+ " <td>Female</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>40.0</td>\n",
+ " <td>Cuba</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " age workclass fnlwgt education education-num \\\n",
+ "0 39.0 State-gov 77516.0 Bachelors 13.0 \n",
+ "1 50.0 Self-emp-not-inc 83311.0 Bachelors 13.0 \n",
+ "2 38.0 Private 215646.0 HS-grad 9.0 \n",
+ "3 53.0 Private 234721.0 11th 7.0 \n",
+ "4 28.0 Private 338409.0 Bachelors 13.0 \n",
+ "\n",
+ " marital-status occupation relationship race sex \\\n",
+ "0 Never-married Adm-clerical Not-in-family White Male \n",
+ "1 Married-civ-spouse Exec-managerial Husband White Male \n",
+ "2 Divorced Handlers-cleaners Not-in-family White Male \n",
+ "3 Married-civ-spouse Handlers-cleaners Husband Black Male \n",
+ "4 Married-civ-spouse Prof-specialty Wife Black Female \n",
+ "\n",
+ " capital-gain capital-loss hours-per-week native-country \n",
+ "0 2174.0 0.0 40.0 United-States \n",
+ "1 0.0 0.0 13.0 United-States \n",
+ "2 0.0 0.0 40.0 United-States \n",
+ "3 0.0 0.0 40.0 United-States \n",
+ "4 0.0 0.0 40.0 Cuba "
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "X_train.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Warning: Custom metrics will not be evaluated because there are no test datasets\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "<catboost.core.CatBoostClassifier at 0x7fe0d1ac77f0>"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# If you want to find out how we found these parameters check \"Simple classification \n",
+ "# example with missing feature handling and parameter tuning\" tutorial in `classification`\n",
+ "# subdirectory of tutorials\n",
+ "model = cb.CatBoostClassifier(\n",
+ " class_names=('<=50K', '>50K'),\n",
+ " loss_function='Logloss',\n",
+ " eval_metric='AUC', \n",
+ " custom_metric=['AUC'],\n",
+ " iterations=100,\n",
+ " random_seed=20181224,\n",
+ " learning_rate=0.4234185321620083, \n",
+ " depth=5, \n",
+ " l2_leaf_reg=9.464266235679002)\n",
+ "model.fit(\n",
+ " cb.Pool(X_train, y_train, cat_features=np.where(X_train.dtypes != np.float)[0]),\n",
+ " verbose=False)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model.save_model('adult.cbm')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "156K\tadult.cbm\r\n"
+ ]
+ }
+ ],
+ "source": [
+ "!du -sh adult.cbm"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "We got the model, now it's time to use it via `catboost` package for Rust. Next part of the tutorial\n",
+ "will be in a Cargo project."
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.3"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
From 85f96382e6d913ab7098f25fe7194930d751e817 Mon Sep 17 00:00:00 2001
From: Serg Gini <kornburn@gmail.com>
Date: Sun, 30 Jul 2023 03:37:02 +0400
Subject: [PATCH 2/3] Added dlang tutorial
D language tutorial used ImportC functionality to automatically create bindings from c_api.h header file
---
apply_model/clang/readme.md | 2 +-
apply_model/dlang/readme.md | 25 +++-
apply_model/dlang/src/lib_import.c | 1 +
apply_model/dlang/src/main.d | 215 +++++++++++++++++-----------
apply_model/dlang/train_model.ipynb | 6 +-
5 files changed, 154 insertions(+), 95 deletions(-)
create mode 100644 apply_model/dlang/src/lib_import.c
diff --git a/apply_model/clang/readme.md b/apply_model/clang/readme.md
index 13b54a5..b6a819f 100644
--- a/apply_model/clang/readme.md
+++ b/apply_model/clang/readme.md
@@ -3,7 +3,7 @@ This tutorial consists of two parts:
- first part where we preprocess dataset and train the classifier model.
This part can be found in [train_model.ipynb](train_model.ipynb).
- second part where we load model into C application and then apply it.
- This part presented as a C file. At first you need to build a library, as it is suggested on [](https://catboost.ai/en/docs/concepts/c-plus-plus-api_dynamic-c-pluplus-wrapper). To run, you can execute:
+ This part presented as a C file. At first you need to build a library, as it is suggested on [Evaluation library](https://catboost.ai/en/docs/concepts/c-plus-plus-api_dynamic-c-pluplus-wrapper). To run, you can execute:
* in case Linux/macOS
`clang <your sources and options> -L<path_to_dir_with_libcatboostmodel> -lcatboostmodel`
diff --git a/apply_model/dlang/readme.md b/apply_model/dlang/readme.md
index 61cbd0c..f48f526 100644
--- a/apply_model/dlang/readme.md
+++ b/apply_model/dlang/readme.md
@@ -1,7 +1,24 @@
-# Apply CatBoost model from Rust
+# Apply CatBoost model from D
This tutorial consists of two parts:
- first part where we preprocess dataset and train the classifier model.
This part can be found in [train_model.ipynb](train_model.ipynb).
-- second part where we load model into Rust application and then apply it.
- This part presented as a small Cargo project. To run, execute `cargo run --release`.
- If you just want to look at code snippets you can go directly to [src/main.rs](src/main.rs).
+- second part where we load model into D application and then apply it.
+ This part presented as a D file. At first you need to build a library, as it is suggested on [Evaluation library](https://catboost.ai/en/docs/concepts/c-plus-plus-api_dynamic-c-pluplus-wrapper).
+
+ After that you need to generate preprocessed header file (.i) for ImportC functionality. To prepare preprocessed header you need to create a file [lib_import.c](src/lib_import.c) consists of one line
+
+ `#include <path_to_header_file/c_api.h>`
+
+ and use available C compiler (or built-in preprocessor in D compiler) as suggested on the page of [ImportC Documentation](https://dlang.org/spec/importc.html):
+
+ `clang -E lib_import.c -o lib_import.i`
+
+ To run, you can execute:
+ * in case Linux/macOS
+
+ `ldc2 <your sources and options> <your_preprocessed_header_file> -L<path_to_dir_with_libcatboostmodel>/libcatboostmodel.{so/dylib}`
+ * in case Windows
+
+ `ldc2.exe <your sources and options> <your_preprocessed_header_file> /link <path_to_dir_with_libcatboostmodel>\catboostmodel.{lib/dll}`
+
+ If you just want to look at code snippets you can go directly to [src/main.d](src/main.d).
diff --git a/apply_model/dlang/src/lib_import.c b/apply_model/dlang/src/lib_import.c
new file mode 100644
index 0000000..c7ef90a
--- /dev/null
+++ b/apply_model/dlang/src/lib_import.c
@@ -0,0 +1 @@
+#include </path_to_header_file/c_api.h>
diff --git a/apply_model/dlang/src/main.d b/apply_model/dlang/src/main.d
index 8a9242a..9463e94 100644
--- a/apply_model/dlang/src/main.d
+++ b/apply_model/dlang/src/main.d
@@ -1,29 +1,40 @@
+import std.stdio;
+import std.math : exp;
+
// Bring catboost module into the scope
-use catboost;
+import lib_import;
-fn sigmoid(x: f64) -> f64 {
- 1. / (1. + (-x).exp())
+double sigmoid(double x)
+{
+ return 1. / (1. + exp(-x));
}
-fn answer(makes_over_50k_a_year: bool) -> &'static str {
- if makes_over_50k_a_year {
- "makes over 50K a year"
- } else {
- "doesn't make over 50K a year"
+string answer(bool makes_over_50k_a_year)
+{
+ if (makes_over_50k_a_year)
+ {
+ return "makes over 50k a year";
+ }
+ else
+ {
+ return "doesn't make over 50k a year";
}
}
-fn main() {
+void main(string[] args)
+{
// Load "adult.cbm" model that we trained withing Jupyter Notebook
- let model_path = "adult.cbm";
- let model = catboost::Model::load(model_path).unwrap();
-
+ ModelCalcerHandle* modelHandle = ModelCalcerCreate();
+ if (!(modelHandle.LoadFullModelFromFile("adult.cbm")))
+ {
+ writeln("LoadFullModelFromFile error message: %s", GetErrorString());
+ }
// You can also try to load your own model just replace "adult.cbm" with path to your model that classifies data
// from UCI Adult Dataset.
- println!("Adult dataset model metainformation\n");
+ writeln("Adult dataset model metainformation\n");
- println!("tree count: {}", model.get_tree_count());
+ writeln("tree count: ", modelHandle.GetTreeCount());
// In our case we were solving a binary classification problem (weather person makes over 50K a year), so the
// dimension of the prediction will be 1, it will return probability of the object to belong to the positive
@@ -34,11 +45,11 @@ fn main() {
//
// For most of cases prediction dimension will be 1 (for regression and for ranking), it can be N for cases of
// multiclassification, where N is a number of classes.
- println!("prediction dimension: {}", model.get_dimensions_count());
+ writeln("prediction dimension: ", modelHandle.GetDimensionsCount());
- println!("numeric feature count: {}", model.get_float_features_count());
+ writeln("numeric feature count: ", modelHandle.GetFloatFeaturesCount());
- println!("categoric feature count: {}", model.get_cat_features_count());
+ writeln("categoric feature count: ", modelHandle.GetCatFeaturesCount());
// Ok now lets try to use our model for prediction. We'll look at the test part of Adult dataset. You will need
// to download it [1] from UCI repository. Look for "adult.test", "adult.name" will also be useful because it
@@ -62,44 +73,52 @@ fn main() {
//
// [1]: https://archive.ics.uci.edu/ml/machine-learning-databases/adult/
- println!();
-
- let person_a_numeric_features = vec![25., 226_802., 7., 0., 0., 40.];
- let person_a_categoric_features = vec![
- String::from("Private"),
- String::from("11th"),
- String::from("Never-married"),
- String::from("Machine-op-inspct"),
- String::from("Own-child"),
- String::from("Black"),
- String::from("Male"),
- String::from("United-States"),
+ writeln();
+
+ const(float)[6] pers_a_num_feat = [25., 226_802., 7., 0., 0., 40.];
+ const(char)*[8] pers_a_cat_feat = [
+ "Private".ptr,
+ "11th".ptr,
+ "Never-married".ptr,
+ "Machine-op-inspct".ptr,
+ "Own-child".ptr,
+ "Black".ptr,
+ "Male".ptr,
+ "United-States".ptr
];
- let person_a_prediction = model
- .calc_model_prediction(
- vec![person_a_numeric_features.clone()],
- vec![person_a_categoric_features.clone()],
- )
- .unwrap();
+
+ double[1] result_a;
+
+ auto a_num_feat_ptr = pers_a_num_feat.ptr;
+ auto a_cat_feat_ptr = pers_a_cat_feat.ptr;
+
+ if (!modelHandle.CalcModelPrediction(
+ 1,
+ &a_num_feat_ptr, 6,
+ &a_cat_feat_ptr, 8,
+ result_a.ptr, 1))
+ {
+ writeln("CalcModelPrediction error message: ", GetErrorString());
+ }
// Since we made prediction only for one person and prediction dimension is 1, proability of person A make
// over 50K will have index 0 in `person_a_prediction`.
//
// CatBoost doesn't compute "probability", to turn CatBoost prediction into a probability we'll need to apply
// sigmoid function.
- let person_a_makes_over_50k_probability = sigmoid(person_a_prediction[0]);
- println!(
- "Person A make over 50K a year with probability {}",
- person_a_makes_over_50k_probability
+ double pers_a_makes_over_50k_prob = sigmoid(result_a[0]);
+ writeln(
+ "Person A make over 50K a year with probability ",
+ pers_a_makes_over_50k_prob
);
// When we were training CatBoost we used a default classification threshold for AUC which is equal to 0.5,
// this means that our formula is optimized for this threashold, though we may change threshold to optimize some
// other metric on a different dataset, but we won't do it in this tutorial.
- let classification_threshold = 0.5;
+ double classification_threshold = 0.5;
- let person_a_makes_over_50k = person_a_makes_over_50k_probability > classification_threshold;
- println!("Person A {}", answer(person_a_makes_over_50k));
+ bool pers_a_makes_over_50k = pers_a_makes_over_50k_prob > classification_threshold;
+ writeln("Person A ", answer(pers_a_makes_over_50k));
// Now lets find an example with missing features and income greater than 50K a year. At line 40 of "adult.test"
// we can find following line:
@@ -117,60 +136,82 @@ fn main() {
// And according to the dataset Person B makes more than 50K a year. Ok, lets try to apply the model to this
// example.
- println!();
-
- let person_b_numeric_features = vec![40., 85019., 16., 0., 0., 45.];
- let person_b_categoric_features = vec![
- String::from("Private"),
- String::from("Doctorate"),
- String::from("Married-civ-spouce"),
- String::from("Prof-specialty"),
- String::from("Husband"),
- String::from("Asian-Pac-Islander"),
- String::from("Male"),
- String::from("nan"),
+ writeln();
+
+ const(float)[6] pers_b_num_feat = [40., 85_019., 16., 0., 0., 45.];
+ const(char)*[8] pers_b_cat_feat = [
+ "Private".ptr,
+ "Doctorate".ptr,
+ "Married-civ-spouce".ptr,
+ "Prof-specialty".ptr,
+ "Husband".ptr,
+ "Asian-Pac-Islander".ptr,
+ "Male".ptr,
+ "nan".ptr
];
- let person_b_prediction = model
- .calc_model_prediction(
- vec![person_b_numeric_features.clone()],
- vec![person_b_categoric_features.clone()],
- )
- .unwrap();
- let person_b_makes_over_50k_probability = sigmoid(person_b_prediction[0]);
- let person_b_makes_over_50k = person_b_makes_over_50k_probability > classification_threshold;
- println!(
- "Person B make over 50K a year with probability {}",
- person_b_makes_over_50k_probability
+
+ double[1] result_b;
+
+ auto b_num_feat_ptr = pers_b_num_feat.ptr;
+ auto b_cat_feat_ptr = pers_b_cat_feat.ptr;
+
+ if (!modelHandle.CalcModelPrediction(
+ 1,
+ &b_num_feat_ptr, 6,
+ &b_cat_feat_ptr, 8,
+ result_b.ptr, 1))
+ {
+ writeln("CalcModelPrediction error message: ", GetErrorString());
+ }
+
+ double pers_b_makes_over_50k_prob = sigmoid(result_b[0]);
+ bool pers_b_makes_over_50k = pers_b_makes_over_50k_prob > classification_threshold;
+ writeln(
+ "Person B make over 50K a year with probability ",
+ pers_b_makes_over_50k_prob
);
- println!("Person B {}", answer(person_b_makes_over_50k));
+ writeln("Person B ", answer(pers_b_makes_over_50k));
// Let's try to apply the model to Person A and Person B in one call.
- println!();
-
- let persons_ab_numberic_features = vec![person_a_numeric_features, person_b_numeric_features];
- let persons_ab_categoric_features = vec![person_a_categoric_features, person_b_categoric_features];
- let persons_ab_predictions = model
- .calc_model_prediction(persons_ab_numberic_features, persons_ab_categoric_features)
- .unwrap();
- let persons_ab_make_over_50k_probabilities =
- vec![sigmoid(persons_ab_predictions[0]), sigmoid(persons_ab_predictions[1])];
- let persons_ab_make_over_50k = vec![
- persons_ab_make_over_50k_probabilities[0] > classification_threshold,
- persons_ab_make_over_50k_probabilities[1] > classification_threshold,
+ writeln();
+
+ const(float)*[2] pers_ab_num_feat = cast(const(float)*[2])[pers_a_num_feat, pers_b_num_feat];
+ const(char)**[2] pers_ab_cat_feat = cast(const(char)**[2])[pers_a_cat_feat, pers_b_cat_feat];
+
+ double[2] result_ab;
+
+ auto ab_num_feat_ptr = cast(const(float)**)pers_ab_num_feat;
+ auto ab_cat_feat_ptr = cast(const(char)***)pers_ab_cat_feat;
+
+ if (!modelHandle.CalcModelPrediction(
+ 2,
+ ab_num_feat_ptr, 6,
+ ab_cat_feat_ptr, 8,
+ result_ab.ptr, 2))
+ {
+ writeln("CalcModelPrediction error message: ", GetErrorString());
+ }
+
+ double[2] pers_ab_makes_over_50k_prob = [sigmoid(result_ab[0]), sigmoid(result_ab[1])];
+ bool[2] pers_ab_makes_over_50k = [
+ pers_ab_makes_over_50k_prob[0] > classification_threshold,
+ pers_ab_makes_over_50k_prob[1] > classification_threshold
];
- println!("Using batch interface");
+ writeln("Using batch interface");
// Predictions should be same as above
- println!(
- "Person A make over 50K a year with probability {}",
- persons_ab_make_over_50k_probabilities[0]
+ writeln(
+ "Person A make over 50K a year with probability ",
+ pers_ab_makes_over_50k_prob[0]
);
- println!("Person A {}", answer(persons_ab_make_over_50k[0]));
- println!(
- "Person B make over 50K a year with probability {}",
- persons_ab_make_over_50k_probabilities[1]
+ writeln("Person A ", answer(pers_ab_makes_over_50k[0]));
+ writeln(
+ "Person B make over 50K a year with probability ",
+ pers_ab_makes_over_50k_prob[1]
);
- println!("Person B {}", answer(persons_ab_make_over_50k[1]));
+ writeln("Person B ", answer(pers_ab_makes_over_50k[1]));
+
+ modelHandle.ModelCalcerDelete();
}
diff --git a/apply_model/dlang/train_model.ipynb b/apply_model/dlang/train_model.ipynb
index 5de4826..10f9ca1 100644
--- a/apply_model/dlang/train_model.ipynb
+++ b/apply_model/dlang/train_model.ipynb
@@ -4,7 +4,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# catboost for rust tutorial"
+ "# catboost for dlang tutorial"
]
},
{
@@ -344,8 +344,8 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "We got the model, now it's time to use it via `catboost` package for Rust. Next part of the tutorial\n",
- "will be in a Cargo project."
+ "We got the model, now it's time to use it via `catboost` package for D. Next part of the tutorial\n",
+ "will be in a D project."
]
}
],
From 3c8a3ee90a4bf6f5024aea2b50c079b2ea31ddcb Mon Sep 17 00:00:00 2001
From: Serg Gini <kornburn@gmail.com>
Date: Sun, 30 Jul 2023 21:53:11 +0400
Subject: [PATCH 3/3] Update main.d
Fixed strings literals, because in D they are already 0-terminated
---
apply_model/dlang/src/main.d | 38 ++++++++++++++++++------------------
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/apply_model/dlang/src/main.d b/apply_model/dlang/src/main.d
index 9463e94..39a1e81 100644
--- a/apply_model/dlang/src/main.d
+++ b/apply_model/dlang/src/main.d
@@ -77,17 +77,17 @@ void main(string[] args)
const(float)[6] pers_a_num_feat = [25., 226_802., 7., 0., 0., 40.];
const(char)*[8] pers_a_cat_feat = [
- "Private".ptr,
- "11th".ptr,
- "Never-married".ptr,
- "Machine-op-inspct".ptr,
- "Own-child".ptr,
- "Black".ptr,
- "Male".ptr,
- "United-States".ptr
+ "Private",
+ "11th",
+ "Never-married",
+ "Machine-op-inspct",
+ "Own-child",
+ "Black",
+ "Male",
+ "United-States"
];
- double[1] result_a;
+ double[1] result_a = [0];
auto a_num_feat_ptr = pers_a_num_feat.ptr;
auto a_cat_feat_ptr = pers_a_cat_feat.ptr;
@@ -140,17 +140,17 @@ void main(string[] args)
const(float)[6] pers_b_num_feat = [40., 85_019., 16., 0., 0., 45.];
const(char)*[8] pers_b_cat_feat = [
- "Private".ptr,
- "Doctorate".ptr,
- "Married-civ-spouce".ptr,
- "Prof-specialty".ptr,
- "Husband".ptr,
- "Asian-Pac-Islander".ptr,
- "Male".ptr,
- "nan".ptr
+ "Private",
+ "Doctorate",
+ "Married-civ-spouce",
+ "Prof-specialty",
+ "Husband",
+ "Asian-Pac-Islander",
+ "Male",
+ "nan"
];
- double[1] result_b;
+ double[1] result_b = [0];
auto b_num_feat_ptr = pers_b_num_feat.ptr;
auto b_cat_feat_ptr = pers_b_cat_feat.ptr;
@@ -179,7 +179,7 @@ void main(string[] args)
const(float)*[2] pers_ab_num_feat = cast(const(float)*[2])[pers_a_num_feat, pers_b_num_feat];
const(char)**[2] pers_ab_cat_feat = cast(const(char)**[2])[pers_a_cat_feat, pers_b_cat_feat];
- double[2] result_ab;
+ double[2] result_ab = [0, 0];
auto ab_num_feat_ptr = cast(const(float)**)pers_ab_num_feat;
auto ab_cat_feat_ptr = cast(const(char)***)pers_ab_cat_feat;