Set up basic file structure and added current ipynbs

e70def72 · Matthew K Defenderfer · f8749ea8 · e70def72 · e70def72 · e70def72
Commit e70def72 authored 5 years ago by Matthew K Defenderfer
--- a/ctmodel-ml.yml
+++ b/ctmodel-ml.yml
+name: ctmodel-ml
+channels:
+  - conda-forge
+  - anaconda
+  - defaults
+dependencies:
+  - _tflow_1100_select=0.0.1=gpu
+  - absl-py=0.4.1=py36_0
+  - astor=0.7.1=py36_0
+  - bleach=1.5.0=py36_0
+  - cudatoolkit=9.0=h13b8566_0
+  - cudnn=7.1.2=cuda9.0_0
+  - cupti=9.0.176=0
+  - gast=0.2.0=py36_0
+  - grpcio=1.12.1=py36hdbcaa40_0
+  - hdf5=1.10.2=hba1933b_1
+  - html5lib=0.9999999=py36_0
+  - libprotobuf=3.6.0=hdbcaa40_0
+  - markdown=2.6.11=py36_0
+  - pyyaml=3.13=py36h14c3975_0
+  - termcolor=1.1.0=py36_1
+  - werkzeug=0.14.1=py36_0
+  - yaml=0.1.7=h96e3832_1
+  - nibabel=2.3.0=pyh24bf2e0_1
+  - pydicom=1.1.0=py_0
+  - appdirs=1.4.3=py36h28b3542_0
+  - asn1crypto=0.24.0=py36_0
+  - attrs=18.2.0=py36h28b3542_0
+  - automat=0.7.0=py36_0
+  - backcall=0.1.0=py36_0
+  - blas=1.0=mkl
+  - ca-certificates=2018.03.07=0
+  - certifi=2018.10.15=py36_0
+  - cffi=1.11.5=py36he75722e_1
+  - constantly=15.1.0=py36h28b3542_0
+  - cryptography=2.3.1=py36hc365091_0
+  - cycler=0.10.0=py36_0
+  - cython=0.28.5=py36hf484d3e_0
+  - dbus=1.13.2=h714fa37_1
+  - decorator=4.3.0=py36_0
+  - entrypoints=0.2.3=py36_2
+  - expat=2.2.6=he6710b0_0
+  - fontconfig=2.13.0=h9420a91_0
+  - freetype=2.9.1=h8a8886c_1
+  - future=0.16.0=py36_0
+  - glib=2.56.2=hd408876_0
+  - gmp=6.1.2=h6c8ec71_1
+  - gst-plugins-base=1.14.0=hbbd80ab_1
+  - gstreamer=1.14.0=hb453b48_1
+  - h5py=2.8.0=py36h989c5e5_3
+  - hyperlink=18.0.0=py36_0
+  - icu=58.2=h9c2bf20_1
+  - idna=2.7=py36_0
+  - incremental=17.5.0=py36_0
+  - intel-openmp=2019.0=118
+  - ipykernel=4.9.0=py36_0
+  - ipython=6.5.0=py36_0
+  - ipython_genutils=0.2.0=py36_0
+  - jedi=0.12.1=py36_0
+  - jinja2=2.10=py36_0
+  - jpeg=9b=h024ee3a_2
+  - jsonschema=2.6.0=py36_0
+  - jupyter_client=5.2.3=py36_0
+  - jupyter_core=4.4.0=py36_0
+  - keras-applications=1.0.4=py36_1
+  - keras-base=2.2.2=py36_0
+  - keras-preprocessing=1.0.2=py36_1
+  - kiwisolver=1.0.1=py36hf484d3e_0
+  - libedit=3.1.20170329=h6b74fdf_2
+  - libffi=3.2.1=hd88cf55_4
+  - libgcc-ng=8.2.0=hdf63c60_1
+  - libgfortran-ng=7.3.0=hdf63c60_0
+  - libpng=1.6.34=hb9fc6fc_0
+  - libsodium=1.0.16=h1bed415_0
+  - libstdcxx-ng=8.2.0=hdf63c60_1
+  - libuuid=1.0.3=h1bed415_2
+  - libxcb=1.13=h1bed415_1
+  - libxml2=2.9.8=h26e45fe_1
+  - markupsafe=1.0=py36h14c3975_1
+  - matplotlib=2.2.3=py36hb69df0a_0
+  - mistune=0.8.3=py36h14c3975_1
+  - mkl=2019.0=118
+  - mkl_fft=1.0.4=py36h4414c95_1
+  - mkl_random=1.0.1=py36h4414c95_1
+  - nbconvert=5.3.1=py36_0
+  - nbformat=4.4.0=py36_0
+  - ncurses=6.1=hf484d3e_0
+  - notebook=5.6.0=py36_0
+  - numpy=1.14.5=py36h1b885b7_4
+  - numpy-base=1.14.5=py36hdbf6ddf_4
+  - openssl=1.0.2p=h14c3975_0
+  - pandas=0.23.4=py36h04863e7_0
+  - pandoc=2.2.3.2=0
+  - pandocfilters=1.4.2=py36_1
+  - parso=0.3.1=py36_0
+  - patsy=0.5.0=py36_0
+  - pcre=8.42=h439df22_0
+  - pexpect=4.6.0=py36_0
+  - pickleshare=0.7.4=py36_0
+  - pip=10.0.1=py36_0
+  - prometheus_client=0.3.1=py36h28b3542_0
+  - prompt_toolkit=1.0.15=py36_0
+  - protobuf=3.6.0=py36hf484d3e_0
+  - ptyprocess=0.6.0=py36_0
+  - pyasn1=0.4.4=py36h28b3542_0
+  - pyasn1-modules=0.2.2=py36_0
+  - pycparser=2.18=py36_1
+  - pydot=1.2.4=py36_0
+  - pygments=2.2.0=py36_0
+  - pyopenssl=18.0.0=py36_0
+  - pyparsing=2.2.0=py36_1
+  - pyqt=5.9.2=py36h05f1152_2
+  - python=3.6.6=hc3d631a_0
+  - python-dateutil=2.7.3=py36_0
+  - pytz=2018.5=py36_0
+  - pyzmq=17.1.2=py36h14c3975_0
+  - qt=5.9.6=h8703b6f_2
+  - readline=7.0=h7b6447c_5
+  - scikit-learn=0.20.0=py36h4989274_1
+  - scipy=1.1.0=py36hd20e5f9_0
+  - seaborn=0.9.0=py36_0
+  - send2trash=1.5.0=py36_0
+  - service_identity=17.0.0=py36h28b3542_0
+  - setuptools=39.1.0=py36_0
+  - simplegeneric=0.8.1=py36_2
+  - sip=4.19.8=py36hf484d3e_0
+  - six=1.11.0=py36_1
+  - sqlite=3.24.0=h84994c4_0
+  - statsmodels=0.9.0=py36h035aef0_0
+  - tensorboard=1.10.0=py36hf484d3e_0
+  - tensorflow=1.10.0=gpu_py36h97a2126_0
+  - tensorflow-base=1.10.0=gpu_py36h6ecc378_0
+  - tensorflow-gpu=1.10.0=hf154084_0
+  - terminado=0.8.1=py36_1
+  - testpath=0.3.1=py36_0
+  - tk=8.6.8=hbc83047_0
+  - tornado=5.1=py36h14c3975_0
+  - traitlets=4.3.2=py36_0
+  - twisted=18.7.0=py36h14c3975_1
+  - wcwidth=0.1.7=py36_0
+  - webencodings=0.5.1=py36_1
+  - wheel=0.31.1=py36_0
+  - xz=5.2.4=h14c3975_4
+  - zeromq=4.2.5=hf484d3e_1
+  - zlib=1.2.11=ha838bed_2
+  - zope=1.0=py36_1
+  - zope.interface=4.5.0=py36h14c3975_0
+  - pip:
+    - blinker==1.4
+    - chardet==3.0.4
+    - cloudpickle==0.5.6
+    - configparser==3.5.0
+    - dask==0.19.1
+    - kaggle==1.4.7.1
+    - keras==2.2.2
+    - keras-vis==0.4.1
+    - networkx==2.2rc1
+    - packaging==17.1
+    - pillow==5.2.0
+    - pyhamcrest==1.9.0
+    - python-slugify==1.2.6
+    - pywavelets==1.0.0
+    - requests==2.19.1
+    - scikit-image==0.14.0
+    - simpleitk==1.1.0
+    - toolz==0.9.0
+    - tqdm==4.26.0
+    - unidecode==1.0.22
+    - urllib3==1.22
+    - xgboost==0.90
--- a/model-py/regression-MKD.ipynb
+++ b/model-py/regression-MKD.ipynb
--- a/model-py/regression.ipynb
+++ b/model-py/regression.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn import linear_model\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import tree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.datasets import load_boston\n",
+    "boston =load_boston()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(506, 13)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (boston.data.shape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[6.3200e-03 1.8000e+01 2.3100e+00 ... 1.5300e+01 3.9690e+02 4.9800e+00]\n",
+      " [2.7310e-02 0.0000e+00 7.0700e+00 ... 1.7800e+01 3.9690e+02 9.1400e+00]\n",
+      " [2.7290e-02 0.0000e+00 7.0700e+00 ... 1.7800e+01 3.9283e+02 4.0300e+00]\n",
+      " ...\n",
+      " [6.0760e-02 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9690e+02 5.6400e+00]\n",
+      " [1.0959e-01 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9345e+02 6.4800e+00]\n",
+      " [4.7410e-02 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9690e+02 7.8800e+00]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print (boston.data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# df_x are your input features\n",
+    "df_x=pd.DataFrame(boston.data,columns=boston.feature_names)\n",
+    "\n",
+    "# df_y is your output feature (the one you want to predict)\n",
+    "df_y=pd.DataFrame(boston.target)"
+   ]
+  },
+  {
+   "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>CRIM</th>\n",
+       "      <th>ZN</th>\n",
+       "      <th>INDUS</th>\n",
+       "      <th>CHAS</th>\n",
+       "      <th>NOX</th>\n",
+       "      <th>RM</th>\n",
+       "      <th>AGE</th>\n",
+       "      <th>DIS</th>\n",
+       "      <th>RAD</th>\n",
+       "      <th>TAX</th>\n",
+       "      <th>PTRATIO</th>\n",
+       "      <th>B</th>\n",
+       "      <th>LSTAT</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "      <td>506.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>3.613524</td>\n",
+       "      <td>11.363636</td>\n",
+       "      <td>11.136779</td>\n",
+       "      <td>0.069170</td>\n",
+       "      <td>0.554695</td>\n",
+       "      <td>6.284634</td>\n",
+       "      <td>68.574901</td>\n",
+       "      <td>3.795043</td>\n",
+       "      <td>9.549407</td>\n",
+       "      <td>408.237154</td>\n",
+       "      <td>18.455534</td>\n",
+       "      <td>356.674032</td>\n",
+       "      <td>12.653063</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>8.601545</td>\n",
+       "      <td>23.322453</td>\n",
+       "      <td>6.860353</td>\n",
+       "      <td>0.253994</td>\n",
+       "      <td>0.115878</td>\n",
+       "      <td>0.702617</td>\n",
+       "      <td>28.148861</td>\n",
+       "      <td>2.105710</td>\n",
+       "      <td>8.707259</td>\n",
+       "      <td>168.537116</td>\n",
+       "      <td>2.164946</td>\n",
+       "      <td>91.294864</td>\n",
+       "      <td>7.141062</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>0.006320</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.460000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.385000</td>\n",
+       "      <td>3.561000</td>\n",
+       "      <td>2.900000</td>\n",
+       "      <td>1.129600</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>187.000000</td>\n",
+       "      <td>12.600000</td>\n",
+       "      <td>0.320000</td>\n",
+       "      <td>1.730000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>0.082045</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>5.190000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.449000</td>\n",
+       "      <td>5.885500</td>\n",
+       "      <td>45.025000</td>\n",
+       "      <td>2.100175</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>279.000000</td>\n",
+       "      <td>17.400000</td>\n",
+       "      <td>375.377500</td>\n",
+       "      <td>6.950000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>0.256510</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>9.690000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.538000</td>\n",
+       "      <td>6.208500</td>\n",
+       "      <td>77.500000</td>\n",
+       "      <td>3.207450</td>\n",
+       "      <td>5.000000</td>\n",
+       "      <td>330.000000</td>\n",
+       "      <td>19.050000</td>\n",
+       "      <td>391.440000</td>\n",
+       "      <td>11.360000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>3.677083</td>\n",
+       "      <td>12.500000</td>\n",
+       "      <td>18.100000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.624000</td>\n",
+       "      <td>6.623500</td>\n",
+       "      <td>94.075000</td>\n",
+       "      <td>5.188425</td>\n",
+       "      <td>24.000000</td>\n",
+       "      <td>666.000000</td>\n",
+       "      <td>20.200000</td>\n",
+       "      <td>396.225000</td>\n",
+       "      <td>16.955000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>88.976200</td>\n",
+       "      <td>100.000000</td>\n",
+       "      <td>27.740000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.871000</td>\n",
+       "      <td>8.780000</td>\n",
+       "      <td>100.000000</td>\n",
+       "      <td>12.126500</td>\n",
+       "      <td>24.000000</td>\n",
+       "      <td>711.000000</td>\n",
+       "      <td>22.000000</td>\n",
+       "      <td>396.900000</td>\n",
+       "      <td>37.970000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "             CRIM          ZN       INDUS        CHAS         NOX          RM  \\\n",
+       "count  506.000000  506.000000  506.000000  506.000000  506.000000  506.000000   \n",
+       "mean     3.613524   11.363636   11.136779    0.069170    0.554695    6.284634   \n",
+       "std      8.601545   23.322453    6.860353    0.253994    0.115878    0.702617   \n",
+       "min      0.006320    0.000000    0.460000    0.000000    0.385000    3.561000   \n",
+       "25%      0.082045    0.000000    5.190000    0.000000    0.449000    5.885500   \n",
+       "50%      0.256510    0.000000    9.690000    0.000000    0.538000    6.208500   \n",
+       "75%      3.677083   12.500000   18.100000    0.000000    0.624000    6.623500   \n",
+       "max     88.976200  100.000000   27.740000    1.000000    0.871000    8.780000   \n",
+       "\n",
+       "              AGE         DIS         RAD         TAX     PTRATIO           B  \\\n",
+       "count  506.000000  506.000000  506.000000  506.000000  506.000000  506.000000   \n",
+       "mean    68.574901    3.795043    9.549407  408.237154   18.455534  356.674032   \n",
+       "std     28.148861    2.105710    8.707259  168.537116    2.164946   91.294864   \n",
+       "min      2.900000    1.129600    1.000000  187.000000   12.600000    0.320000   \n",
+       "25%     45.025000    2.100175    4.000000  279.000000   17.400000  375.377500   \n",
+       "50%     77.500000    3.207450    5.000000  330.000000   19.050000  391.440000   \n",
+       "75%     94.075000    5.188425   24.000000  666.000000   20.200000  396.225000   \n",
+       "max    100.000000   12.126500   24.000000  711.000000   22.000000  396.900000   \n",
+       "\n",
+       "            LSTAT  \n",
+       "count  506.000000  \n",
+       "mean    12.653063  \n",
+       "std      7.141062  \n",
+       "min      1.730000  \n",
+       "25%      6.950000  \n",
+       "50%     11.360000  \n",
+       "75%     16.955000  \n",
+       "max     37.970000  "
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# prints out bunch os statistics\n",
+    "df_x.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Linear models\n",
+    "#reg=linear_model.LinearRegression()\n",
+    "#reg=linear_model.Ridge(alpha=0.9)\n",
+    "reg=linear_model.Lasso(alpha=0.1)\n",
+    "#reg=linear_model.Lars()\n",
+    "\n",
+    "# non linear model\n",
+    "#reg=tree.DecisionTreeRegressor(max_depth=10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 0.2 refers to 20% of all input data will be used to test the model and the remaining 80% to train the model\n",
+    "# x_train y_train 80% of data that are used for training\n",
+    "# x_test y_test 20% of data that are used for testing your model\n",
+    "\n",
+    "x_train,x_test,y_train,y_test = train_test_split(df_x,df_y,test_size=0.2, random_state=4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Lasso(alpha=0.1, copy_X=True, fit_intercept=True, max_iter=1000,\n",
+       "   normalize=False, positive=False, precompute=False, random_state=None,\n",
+       "   selection='cyclic', tol=0.0001, warm_start=False)"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# this is where your model is being trained\n",
+    "\n",
+    "reg.fit(x_train,y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# for linear models you can enable the following comment and check out all the coefficients of yout linear model\n",
+    "#reg.coef_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# the 20% of the test data that are used for testing purpose\n",
+    "a=reg.predict(x_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[11.35769564],\n",
+       "       [26.63065774],\n",
+       "       [17.07212795],\n",
+       "       [14.88066872],\n",
+       "       [36.41257162],\n",
+       "       [24.9585628 ],\n",
+       "       [31.94678858],\n",
+       "       [18.71968836],\n",
+       "       [18.03333259],\n",
+       "       [24.31205853],\n",
+       "       [29.37517697],\n",
+       "       [28.21096667],\n",
+       "       [19.31608322],\n",
+       "       [29.77081668],\n",
+       "       [22.02956911],\n",
+       "       [15.80101535],\n",
+       "       [21.40010518],\n",
+       "       [11.55888929],\n",
+       "       [10.03696639],\n",
+       "       [14.21676695],\n",
+       "       [ 5.93013576],\n",
+       "       [20.67875375],\n",
+       "       [20.28901268],\n",
+       "       [22.045776  ],\n",
+       "       [16.91359062],\n",
+       "       [20.01181348],\n",
+       "       [14.60702376],\n",
+       "       [14.47106462],\n",
+       "       [19.94873173],\n",
+       "       [16.80168678],\n",
+       "       [14.47686108],\n",
+       "       [23.94606474],\n",
+       "       [35.12159987],\n",
+       "       [22.18768349],\n",
+       "       [17.36984591],\n",
+       "       [19.82812892],\n",
+       "       [30.64690326],\n",
+       "       [35.83418403],\n",
+       "       [24.01776652],\n",
+       "       [24.25497155],\n",
+       "       [36.65259504],\n",
+       "       [31.76859732],\n",
+       "       [19.93445419],\n",
+       "       [31.94878121],\n",
+       "       [30.55626307],\n",
+       "       [24.85315173],\n",
+       "       [40.25718892],\n",
+       "       [17.35967841],\n",
+       "       [20.58594129],\n",
+       "       [23.65915748],\n",
+       "       [33.33055041],\n",
+       "       [25.46122166],\n",
+       "       [18.25223929],\n",
+       "       [27.45084254],\n",
+       "       [13.61083007],\n",
+       "       [22.98211928],\n",
+       "       [24.36098849],\n",
+       "       [33.24773708],\n",
+       "       [17.77844029],\n",
+       "       [34.20142858],\n",
+       "       [16.18855141],\n",
+       "       [20.46046193],\n",
+       "       [31.34454514],\n",
+       "       [14.83719596],\n",
+       "       [39.59888611],\n",
+       "       [28.30333095],\n",
+       "       [29.56328051],\n",
+       "       [ 9.50186015],\n",
+       "       [18.44151744],\n",
+       "       [21.6004166 ],\n",
+       "       [23.21248274],\n",
+       "       [22.98510649],\n",
+       "       [23.36802977],\n",
+       "       [27.76775011],\n",
+       "       [16.2541867 ],\n",
+       "       [23.87249049],\n",
+       "       [16.730009  ],\n",
+       "       [25.39057665],\n",
+       "       [14.1120706 ],\n",
+       "       [19.35830505],\n",
+       "       [22.16813444],\n",
+       "       [19.3767848 ],\n",
+       "       [28.29171375],\n",
+       "       [20.01027133],\n",
+       "       [30.10784765],\n",
+       "       [23.22987591],\n",
+       "       [30.21376239],\n",
+       "       [19.89171106],\n",
+       "       [21.10474733],\n",
+       "       [37.4997143 ],\n",
+       "       [31.49817385],\n",
+       "       [41.24683197],\n",
+       "       [18.88741907],\n",
+       "       [37.34892447],\n",
+       "       [20.22051301],\n",
+       "       [23.61804532],\n",
+       "       [23.95396337],\n",
+       "       [22.14526984],\n",
+       "       [12.45469347],\n",
+       "       [21.69669994],\n",
+       "       [ 9.7580847 ],\n",
+       "       [25.09790195]])"
+      ]
+     },
+     "execution_count": 70,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# ensuring that the output has the correct dimensions\n",
+    "a.shape = (a.size, 1)\n",
+    "a"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    26.452889\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 71,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# calculate the mean square error (lower the error better yourmodel is)\n",
+    "np.mean((a-y_test)**2)"
+   ]
+  }
+ ],
+ "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": "3.7.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
+%% Cell type:code id: tags:
+
+``` python
+import pandas as pd
+import numpy as np
+from sklearn import linear_model
+from sklearn.model_selection import train_test_split
+from sklearn import tree
+```
+
+%% Cell type:code id: tags:
+
+``` python
+from sklearn.datasets import load_boston
+boston =load_boston()
+```
+
+%% Cell type:code id: tags:
+
+``` python
+print (boston.data.shape)
+```
+
+%% Output
+
+    (506, 13)
+
+%% Cell type:code id: tags:
+
+``` python
+print (boston.data)
+```
+
+%% Output
+
+    [[6.3200e-03 1.8000e+01 2.3100e+00 ... 1.5300e+01 3.9690e+02 4.9800e+00]
+     [2.7310e-02 0.0000e+00 7.0700e+00 ... 1.7800e+01 3.9690e+02 9.1400e+00]
+     [2.7290e-02 0.0000e+00 7.0700e+00 ... 1.7800e+01 3.9283e+02 4.0300e+00]
+     ...
+     [6.0760e-02 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9690e+02 5.6400e+00]
+     [1.0959e-01 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9345e+02 6.4800e+00]
+     [4.7410e-02 0.0000e+00 1.1930e+01 ... 2.1000e+01 3.9690e+02 7.8800e+00]]
+
+%% Cell type:code id: tags:
+
+``` python
+# df_x are your input features
+df_x=pd.DataFrame(boston.data,columns=boston.feature_names)
+
+# df_y is your output feature (the one you want to predict)
+df_y=pd.DataFrame(boston.target)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# prints out bunch os statistics
+df_x.describe()
+```
+
+%% Output
+
+                 CRIM          ZN       INDUS        CHAS         NOX          RM  \
+    count  506.000000  506.000000  506.000000  506.000000  506.000000  506.000000
+    mean     3.613524   11.363636   11.136779    0.069170    0.554695    6.284634
+    std      8.601545   23.322453    6.860353    0.253994    0.115878    0.702617
+    min      0.006320    0.000000    0.460000    0.000000    0.385000    3.561000
+    25%      0.082045    0.000000    5.190000    0.000000    0.449000    5.885500
+    50%      0.256510    0.000000    9.690000    0.000000    0.538000    6.208500
+    75%      3.677083   12.500000   18.100000    0.000000    0.624000    6.623500
+    max     88.976200  100.000000   27.740000    1.000000    0.871000    8.780000
+    
+                  AGE         DIS         RAD         TAX     PTRATIO           B  \
+    count  506.000000  506.000000  506.000000  506.000000  506.000000  506.000000
+    mean    68.574901    3.795043    9.549407  408.237154   18.455534  356.674032
+    std     28.148861    2.105710    8.707259  168.537116    2.164946   91.294864
+    min      2.900000    1.129600    1.000000  187.000000   12.600000    0.320000
+    25%     45.025000    2.100175    4.000000  279.000000   17.400000  375.377500
+    50%     77.500000    3.207450    5.000000  330.000000   19.050000  391.440000
+    75%     94.075000    5.188425   24.000000  666.000000   20.200000  396.225000
+    max    100.000000   12.126500   24.000000  711.000000   22.000000  396.900000
+    
+                LSTAT
+    count  506.000000
+    mean    12.653063
+    std      7.141062
+    min      1.730000
+    25%      6.950000
+    50%     11.360000
+    75%     16.955000
+    max     37.970000
+
+%% Cell type:code id: tags:
+
+``` python
+# Linear models
+#reg=linear_model.LinearRegression()
+#reg=linear_model.Ridge(alpha=0.9)
+reg=linear_model.Lasso(alpha=0.1)
+#reg=linear_model.Lars()
+
+# non linear model
+#reg=tree.DecisionTreeRegressor(max_depth=10)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# 0.2 refers to 20% of all input data will be used to test the model and the remaining 80% to train the model
+# x_train y_train 80% of data that are used for training
+# x_test y_test 20% of data that are used for testing your model
+
+x_train,x_test,y_train,y_test = train_test_split(df_x,df_y,test_size=0.2, random_state=4)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# this is where your model is being trained
+
+reg.fit(x_train,y_train)
+```
+
+%% Output
+
+    Lasso(alpha=0.1, copy_X=True, fit_intercept=True, max_iter=1000,
+       normalize=False, positive=False, precompute=False, random_state=None,
+       selection='cyclic', tol=0.0001, warm_start=False)
+
+%% Cell type:code id: tags:
+
+``` python
+# for linear models you can enable the following comment and check out all the coefficients of yout linear model
+#reg.coef_
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# the 20% of the test data that are used for testing purpose
+a=reg.predict(x_test)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# ensuring that the output has the correct dimensions
+a.shape = (a.size, 1)
+a
+```
+
+%% Output
+
+    array([[11.35769564],
+           [26.63065774],
+           [17.07212795],
+           [14.88066872],
+           [36.41257162],
+           [24.9585628 ],
+           [31.94678858],
+           [18.71968836],
+           [18.03333259],
+           [24.31205853],
+           [29.37517697],
+           [28.21096667],
+           [19.31608322],
+           [29.77081668],
+           [22.02956911],
+           [15.80101535],
+           [21.40010518],
+           [11.55888929],
+           [10.03696639],
+           [14.21676695],
+           [ 5.93013576],
+           [20.67875375],
+           [20.28901268],
+           [22.045776  ],
+           [16.91359062],
+           [20.01181348],
+           [14.60702376],
+           [14.47106462],
+           [19.94873173],
+           [16.80168678],
+           [14.47686108],
+           [23.94606474],
+           [35.12159987],
+           [22.18768349],
+           [17.36984591],
+           [19.82812892],
+           [30.64690326],
+           [35.83418403],
+           [24.01776652],
+           [24.25497155],
+           [36.65259504],
+           [31.76859732],
+           [19.93445419],
+           [31.94878121],
+           [30.55626307],
+           [24.85315173],
+           [40.25718892],
+           [17.35967841],
+           [20.58594129],
+           [23.65915748],
+           [33.33055041],
+           [25.46122166],
+           [18.25223929],
+           [27.45084254],
+           [13.61083007],
+           [22.98211928],
+           [24.36098849],
+           [33.24773708],
+           [17.77844029],
+           [34.20142858],
+           [16.18855141],
+           [20.46046193],
+           [31.34454514],
+           [14.83719596],
+           [39.59888611],
+           [28.30333095],
+           [29.56328051],
+           [ 9.50186015],
+           [18.44151744],
+           [21.6004166 ],
+           [23.21248274],
+           [22.98510649],
+           [23.36802977],
+           [27.76775011],
+           [16.2541867 ],
+           [23.87249049],
+           [16.730009  ],
+           [25.39057665],
+           [14.1120706 ],
+           [19.35830505],
+           [22.16813444],
+           [19.3767848 ],
+           [28.29171375],
+           [20.01027133],
+           [30.10784765],
+           [23.22987591],
+           [30.21376239],
+           [19.89171106],
+           [21.10474733],
+           [37.4997143 ],
+           [31.49817385],
+           [41.24683197],
+           [18.88741907],
+           [37.34892447],
+           [20.22051301],
+           [23.61804532],
+           [23.95396337],
+           [22.14526984],
+           [12.45469347],
+           [21.69669994],
+           [ 9.7580847 ],
+           [25.09790195]])
+
+%% Cell type:code id: tags:
+
+``` python
+# calculate the mean square error (lower the error better yourmodel is)
+np.mean((a-y_test)**2)
+```
+
+%% Output
+
+    0    26.452889
+    dtype: float64