--- a
+++ b/lasso/FeatureSelectionLasso.ipynb
@@ -0,0 +1,312 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "kernelspec": {
+      "display_name": "R",
+      "language": "R",
+      "name": "ir"
+    },
+    "language_info": {
+      "codemirror_mode": "r",
+      "file_extension": ".r",
+      "mimetype": "text/x-r-source",
+      "name": "R",
+      "pygments_lexer": "r",
+      "version": "3.6.1"
+    },
+    "colab": {
+      "name": "FeatureSelectionLasso.ipynb",
+      "provenance": [],
+      "toc_visible": true
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "miOoR1xDNq4_",
+        "colab_type": "text"
+      },
+      "source": [
+        "# Lasso feature selection\n",
+        "In this notebook we will use lasso for feature selection on:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "f3XbnemZN3Z4",
+        "colab_type": "code",
+        "outputId": "12ce803f-2336-496a-87a6-c8902a105310",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 357
+        }
+      },
+      "source": [
+        "install.packages(\"glmnet\", dependencies=TRUE)\n",
+        "install.packages(\"survival\", dependencies = TRUE)\n",
+        "library(glmnet)\n",
+        "library(survival)"
+      ],
+      "execution_count": 0,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Installing package into ‘/usr/local/lib/R/site-library’\n",
+            "(as ‘lib’ is unspecified)\n",
+            "\n",
+            "Installing package into ‘/usr/local/lib/R/site-library’\n",
+            "(as ‘lib’ is unspecified)\n",
+            "\n",
+            "Installing package into ‘/usr/local/lib/R/site-library’\n",
+            "(as ‘lib’ is unspecified)\n",
+            "\n",
+            "also installing the dependencies ‘mvtnorm’, ‘maxstat’, ‘flexsurv’\n",
+            "\n",
+            "\n",
+            "Warning message in install.packages(\"survminer\", dependencies = TRUE):\n",
+            "“installation of package ‘mvtnorm’ had non-zero exit status”\n",
+            "Warning message in install.packages(\"survminer\", dependencies = TRUE):\n",
+            "“installation of package ‘maxstat’ had non-zero exit status”\n",
+            "Warning message in install.packages(\"survminer\", dependencies = TRUE):\n",
+            "“installation of package ‘flexsurv’ had non-zero exit status”\n",
+            "Warning message in install.packages(\"survminer\", dependencies = TRUE):\n",
+            "“installation of package ‘survminer’ had non-zero exit status”\n"
+          ],
+          "name": "stderr"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "_ZR4qBMuNq5J",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# we get the data that have been prepared\n",
+        "training_data = read.csv('MergedStdTrainingInput.csv')\n",
+        "output_data = read.csv('y_train.csv')\n",
+        "training_data$PatientID <- NULL\n",
+        "output_data$PatientID <- NULL\n",
+        "\n",
+        "x = as.matrix(training_data)\n",
+        "y = Surv(output_data$SurvivalTime, output_data$Event)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "PbkOyX3CfBpY",
+        "colab_type": "code",
+        "outputId": "f4897cc8-e019-47ce-ef74-6a8f43804db1",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 437
+        }
+      },
+      "source": [
+        "# We use a cross validation, measuring the concordance \n",
+        "fit = cv.glmnet(x, y, family = \"cox\", nfolds = 10, type.measure = \"C\")\n",
+        "plot(fit)"
+      ],
+      "execution_count": 101,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nSIJiBwAAIAmKHQAAgCQodgAAAJL4P/V3glHQf3kAAAAAAElFTkSuQmCC",
+            "text/plain": [
+              "plot without title"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "image/png": {
+              "width": 420,
+              "height": 420
+            },
+            "text/plain": {
+              "width": 420,
+              "height": 420
+            }
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6SOuJWXjolCX",
+        "colab_type": "text"
+      },
+      "source": [
+        "Choose `lambda = fit$lambda.min` or `lambda = fit$lambda.1se`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "nC98jdbnNq5Z",
+        "colab_type": "code",
+        "outputId": "c1f92f01-c0a7-4940-d728-719995b2217b",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        }
+      },
+      "source": [
+        "# We use as lambda, the min + 1 standard error to now calculate the model\n",
+        "modelB = glmnet(x, y, family = \"cox\", lambda=fit$lambda.min)\n",
+        "modelB$beta"
+      ],
+      "execution_count": 106,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "62 x 1 sparse Matrix of class \"dgCMatrix\"\n",
+              "                                                     s0\n",
+              "original_shape_Compactness1                   .        \n",
+              "original_shape_Compactness2                   .        \n",
+              "original_shape_Maximum3DDiameter              0.1583921\n",
+              "original_shape_SphericalDisproportion         .        \n",
+              "original_shape_Sphericity                     .        \n",
+              "original_shape_SurfaceArea                    .        \n",
+              "original_shape_SurfaceVolumeRatio             .        \n",
+              "original_shape_VoxelVolume                    0.3367758\n",
+              "original_firstorder_Energy                    .        \n",
+              "original_firstorder_Entropy                   .        \n",
+              "original_firstorder_Kurtosis                  .        \n",
+              "original_firstorder_Maximum                   0.1544755\n",
+              "original_firstorder_Mean                      0.8908783\n",
+              "original_firstorder_MeanAbsoluteDeviation     .        \n",
+              "original_firstorder_Median                    .        \n",
+              "original_firstorder_Minimum                   .        \n",
+              "original_firstorder_Range                     .        \n",
+              "original_firstorder_RootMeanSquared           .        \n",
+              "original_firstorder_Skewness                  .        \n",
+              "original_firstorder_StandardDeviation         .        \n",
+              "original_firstorder_Uniformity                .        \n",
+              "original_firstorder_Variance                  .        \n",
+              "original_glcm_Autocorrelation                 .        \n",
+              "original_glcm_ClusterProminence               1.7945372\n",
+              "original_glcm_ClusterShade                    .        \n",
+              "original_glcm_ClusterTendency                 .        \n",
+              "original_glcm_Contrast                        .        \n",
+              "original_glcm_Correlation                     .        \n",
+              "original_glcm_DifferenceEntropy               .        \n",
+              "original_glcm_DifferenceAverage               .        \n",
+              "original_glcm_JointEnergy                     .        \n",
+              "original_glcm_JointEntropy                    .        \n",
+              "original_glcm_Id                              .        \n",
+              "original_glcm_Idm                             .        \n",
+              "original_glcm_Imc1                            .        \n",
+              "original_glcm_Imc2                            .        \n",
+              "original_glcm_Idmn                            .        \n",
+              "original_glcm_Idn                             .        \n",
+              "original_glcm_InverseVariance                 .        \n",
+              "original_glcm_MaximumProbability              .        \n",
+              "original_glcm_SumAverage                      .        \n",
+              "original_glcm_SumEntropy                      .        \n",
+              "original_glrlm_ShortRunEmphasis               .        \n",
+              "original_glrlm_LongRunEmphasis                .        \n",
+              "original_glrlm_GrayLevelNonUniformity         0.3540632\n",
+              "original_glrlm_RunLengthNonUniformity         .        \n",
+              "original_glrlm_RunPercentage                 -0.3679683\n",
+              "original_glrlm_LowGrayLevelRunEmphasis        .        \n",
+              "original_glrlm_HighGrayLevelRunEmphasis       .        \n",
+              "original_glrlm_ShortRunLowGrayLevelEmphasis   .        \n",
+              "original_glrlm_ShortRunHighGrayLevelEmphasis  .        \n",
+              "original_glrlm_LongRunLowGrayLevelEmphasis    .        \n",
+              "original_glrlm_LongRunHighGrayLevelEmphasis   .        \n",
+              "Mstage                                        0.6065465\n",
+              "Nstage                                        0.4440378\n",
+              "SourceDataset                                -0.7664450\n",
+              "Tstage                                        .        \n",
+              "age                                           0.7516549\n",
+              "Histology_adenocarcinoma                      .        \n",
+              "Histology_large.cell                          .        \n",
+              "Histology_nos                                 0.1019301\n",
+              "Histology_squamous.cell.carcinoma             .        "
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4t4IZzdzoQvW",
+        "colab_type": "text"
+      },
+      "source": [
+        "Extracting the non-zero coefficient. We will use those features in Python to train models Cox Model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "1RqnAEdGhQVk",
+        "colab_type": "code",
+        "outputId": "6e26c950-a6ec-4a85-fdba-0902da996b06",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 51
+        }
+      },
+      "source": [
+        "features = as.matrix(modelB$beta)\n",
+        "row_sub = apply(features, 1, function(row) all(row !=0 ))\n",
+        "selected_features = as.matrix(features[row_sub,])\n",
+        "# write.table(selected_features, 'selected_features.csv')\n",
+        "rownames(selected_features)"
+      ],
+      "execution_count": 107,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              " [1] \"original_shape_Maximum3DDiameter\"     \n",
+              " [2] \"original_shape_VoxelVolume\"           \n",
+              " [3] \"original_firstorder_Maximum\"          \n",
+              " [4] \"original_firstorder_Mean\"             \n",
+              " [5] \"original_glcm_ClusterProminence\"      \n",
+              " [6] \"original_glrlm_GrayLevelNonUniformity\"\n",
+              " [7] \"original_glrlm_RunPercentage\"         \n",
+              " [8] \"Mstage\"                               \n",
+              " [9] \"Nstage\"                               \n",
+              "[10] \"SourceDataset\"                        \n",
+              "[11] \"age\"                                  \n",
+              "[12] \"Histology_nos\"                        "
+            ],
+            "text/latex": "\\begin{enumerate*}\n\\item 'original\\_shape\\_Maximum3DDiameter'\n\\item 'original\\_shape\\_VoxelVolume'\n\\item 'original\\_firstorder\\_Maximum'\n\\item 'original\\_firstorder\\_Mean'\n\\item 'original\\_glcm\\_ClusterProminence'\n\\item 'original\\_glrlm\\_GrayLevelNonUniformity'\n\\item 'original\\_glrlm\\_RunPercentage'\n\\item 'Mstage'\n\\item 'Nstage'\n\\item 'SourceDataset'\n\\item 'age'\n\\item 'Histology\\_nos'\n\\end{enumerate*}\n",
+            "text/markdown": "1. 'original_shape_Maximum3DDiameter'\n2. 'original_shape_VoxelVolume'\n3. 'original_firstorder_Maximum'\n4. 'original_firstorder_Mean'\n5. 'original_glcm_ClusterProminence'\n6. 'original_glrlm_GrayLevelNonUniformity'\n7. 'original_glrlm_RunPercentage'\n8. 'Mstage'\n9. 'Nstage'\n10. 'SourceDataset'\n11. 'age'\n12. 'Histology_nos'\n\n\n",
+            "text/html": [
+              "<style>\n",
+              ".list-inline {list-style: none; margin:0; padding: 0}\n",
+              ".list-inline>li {display: inline-block}\n",
+              ".list-inline>li:not(:last-child)::after {content: \"\\00b7\"; padding: 0 .5ex}\n",
+              "</style>\n",
+              "<ol class=list-inline><li>'original_shape_Maximum3DDiameter'</li><li>'original_shape_VoxelVolume'</li><li>'original_firstorder_Maximum'</li><li>'original_firstorder_Mean'</li><li>'original_glcm_ClusterProminence'</li><li>'original_glrlm_GrayLevelNonUniformity'</li><li>'original_glrlm_RunPercentage'</li><li>'Mstage'</li><li>'Nstage'</li><li>'SourceDataset'</li><li>'age'</li><li>'Histology_nos'</li></ol>\n"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          }
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file