balkian/sitc
1
0
Fork 0
mirror of https://github.com/gsi-upm/sitc synced 2024-11-22 06:22:29 +00:00
Code Issues Releases Wiki Activity

adapted some calls to new scikit version

Browse Source
This commit is contained in:
Oscar Araque 2018-02-23 15:48:59 +01:00
parent a8355e1ee6
commit 6d38d96f16
5 changed files with 629 additions and 736 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
ml1/2_4_Preprocessing.ipynb
View File

@ -56,9 +56,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 1,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from sklearn import datasets\n", "from sklearn import datasets\n",
@ -83,13 +81,11 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 2,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"from sklearn.cross_validation import train_test_split\n", "from sklearn.model_selection import train_test_split\n",
"x_iris, y_iris = iris.data, iris.target\n", "x_iris, y_iris = iris.data, iris.target\n",
"# Test set will be the 25% taken randomly\n", "# Test set will be the 25% taken randomly\n",
"x_train, x_test, y_train, y_test = train_test_split(x_iris, y_iris, test_size=0.25, random_state=33)" "x_train, x_test, y_train, y_test = train_test_split(x_iris, y_iris, test_size=0.25, random_state=33)"
@ -98,9 +94,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 4,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -118,9 +112,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 5,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -191,9 +183,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 10,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"# Standardize the features\n", "# Standardize the features\n",
@ -206,9 +196,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 11,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -306,9 +294,9 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.5.1+" "version": "3.6.3"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 0 "nbformat_minor": 1
} }

77
ml1/2_5_1_kNN_Model.ipynb
View File

@ -71,10 +71,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 1,
"metadata": { "metadata": {},
"collapsed": true
},
"outputs": [], "outputs": [],
"source": [ "source": [
"# library for displaying plots\n", "# library for displaying plots\n",
@ -86,10 +84,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 2,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"## First, we repeat the load and preprocessing steps\n", "## First, we repeat the load and preprocessing steps\n",
@ -99,7 +95,7 @@
"iris = datasets.load_iris()\n", "iris = datasets.load_iris()\n",
"\n", "\n",
"# Training and test spliting\n", "# Training and test spliting\n",
"from sklearn.cross_validation import train_test_split\n", "from sklearn.model_selection import train_test_split\n",
"\n", "\n",
"x_iris, y_iris = iris.data, iris.target\n", "x_iris, y_iris = iris.data, iris.target\n",
"\n", "\n",
@ -139,10 +135,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 3,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -152,7 +146,7 @@
" weights='uniform')" " weights='uniform')"
] ]
}, },
"execution_count": 5, "execution_count": 3,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -170,10 +164,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 4,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -198,9 +190,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 7,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -221,9 +211,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 8,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -251,9 +239,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 12,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -309,9 +295,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 14,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -349,9 +333,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 15, "execution_count": 15,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -369,9 +351,7 @@
}, },
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {},
"collapsed": false
},
"source": [ "source": [
"We see we classify well all the 'setosa' and 'versicolor' samples. " "We see we classify well all the 'setosa' and 'versicolor' samples. "
] ]
@ -392,10 +372,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 16, "execution_count": 8,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -407,7 +385,7 @@
} }
], ],
"source": [ "source": [
"from sklearn.cross_validation import cross_val_score, KFold\n", "from sklearn.model_selection import cross_val_score, KFold\n",
"from sklearn.pipeline import Pipeline\n", "from sklearn.pipeline import Pipeline\n",
"from sklearn.preprocessing import StandardScaler\n", "from sklearn.preprocessing import StandardScaler\n",
"\n", "\n",
@ -418,8 +396,7 @@
"])\n", "])\n",
"\n", "\n",
"# create a k-fold cross validation iterator of k=10 folds\n", "# create a k-fold cross validation iterator of k=10 folds\n",
"\n", "cv = KFold(10, shuffle=True, random_state=33)\n",
"cv = KFold(x_iris.shape[0], 10, shuffle=True, random_state=33)\n",
"\n", "\n",
"# by default the score used is the one returned by score method of the estimator (accuracy)\n", "# by default the score used is the one returned by score method of the estimator (accuracy)\n",
"scores = cross_val_score(model, x_iris, y_iris, cv=cv)\n", "scores = cross_val_score(model, x_iris, y_iris, cv=cv)\n",
@ -437,10 +414,8 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 17, "execution_count": 9,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
@ -481,9 +456,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": 18,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -568,9 +541,9 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.5.1+" "version": "3.6.3"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 0 "nbformat_minor": 1
} }

153
ml1/2_5_2_Decision_Tree_Model.ipynb
View File

File diff suppressed because one or more lines are too long

1089
ml1/2_6_Model_Tuning.ipynb
View File

File diff suppressed because it is too large Load Diff

14
ml1/2_7_Model_Persistence.ipynb
View File

@ -56,9 +56,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 1,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -79,7 +77,7 @@
"iris = datasets.load_iris()\n", "iris = datasets.load_iris()\n",
"\n", "\n",
"# Training and test spliting\n", "# Training and test spliting\n",
"from sklearn.cross_validation import train_test_split\n", "from sklearn.model_selection import train_test_split\n",
"x_iris, y_iris = iris.data, iris.target\n", "x_iris, y_iris = iris.data, iris.target\n",
"# Test set will be the 25% taken randomly\n", "# Test set will be the 25% taken randomly\n",
"x_train, x_test, y_train, y_test = train_test_split(x_iris, y_iris, test_size=0.25, random_state=33)\n", "x_train, x_test, y_train, y_test = train_test_split(x_iris, y_iris, test_size=0.25, random_state=33)\n",
@ -109,9 +107,7 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 2,
"metadata": { "metadata": {},
"collapsed": false
},
"outputs": [ "outputs": [
{ {
"data": { "data": {
@ -196,9 +192,9 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.5.1+" "version": "3.6.3"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 0 "nbformat_minor": 1
} }