{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "LBdSH0Yg6XoH"
},
"source": [
"Load Li
aries"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "52VtTLi0EE7r"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import seaborn as sns\n",
"import numpy as np\n",
"from collections import Counter\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.pyplot import figure\n",
"from pickle import dump\n",
"from pickle import load"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "btQItuEQMuS_"
},
"outputs": [],
"source": [
"def warn(*args, **kwargs):\n",
" pass\n",
"import warnings\n",
"warnings.warn = warn\n",
"\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.tree import DecisionTreeClassifier\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.neighbors import KNeighborsClassifier\n",
"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
"from sklearn.decomposition import PCA\n",
"from sklearn.naive_bayes import GaussianNB\n",
"from sklearn.svm import SVC\n",
"from sklearn.model_selection import KFold\n",
"from sklearn.model_selection import cross_val_score\n",
"from sklearn.model_selection import cross_validate\n",
"from sklearn.metrics import cohen_kappa_score\n",
"from sklearn.metrics import confusion_matrix\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.metrics import plot_confusion_matrix\n",
"from sklearn import tree\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.metrics import roc_curve\n",
"from sklearn.metrics import roc_auc_score\n",
"from sklearn.metrics import plot_roc_curve\n",
"from sklearn.metrics import precision_recall_curve\n",
"from sklearn.metrics import f1_score\n",
"from sklearn.metrics import auc\n",
"from sklearn.metrics import precision_score\n",
"from sklearn.metrics import recall_score\n",
"from sklearn.metrics import make_scorer"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"id": "DQ4gQmpQMv7X"
},
"outputs": [],
"source": [
"from sklearn.model_selection import train_test_split, GridSearchCV, RepeatedStratifiedKFold\n",
"from sklearn.feature_selection import RFECV, SelectKBest\n",
"from imblearn.under_sampling import RandomUnderSampler\n",
"from imblearn.over_sampling import SMOTE\n",
"from sklearn.preprocessing import StandardScaler\n",
"from imblearn.pipeline import Pipeline"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "EvaThE8LQkIH"
},
"source": [
"# Python Project Template\n",
"# 1. Prepare Problem\n",
"# a) Load li
aries\n",
"# b) Load dataset\n",
"# 2. Summarize Data\n",
"# a) Descriptive statistics\n",
"# b) Data visualizations\n",
"# 3. Prepare Data\n",
"# a) Data Cleaning\n",
"# b) Feature Selection\n",
"# c) Data Transforms\n",
"# 4. Evaluate Algorithms\n",
"# a) Split-out validation dataset\n",
"# b) Test options and evaluation metric\n",
"# c) Spot Check Algorithms\n",
"# d) Compare Algorithms\n",
"# 5. Improve Accuracy\n",
"# a) Algorithm Tuning\n",
"# b) Ensembles\n",
"# 6. Finalize Model\n",
"# a) Predictions on validation dataset\n",
"# b) Create standalone model on entire training dataset\n",
"# c) Save model for later use"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
" Load dataset"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "2wUOXeYtEhIH"
},
"outputs": [],
"source": [
"data = pd.read_csv(\"data.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https:
localhost:8080/",
"height": 372
},
"id": "BjTO4L74FiXn",
"outputId": "c87a1064-600d-4126-cf48-fcfdbec4dd65"
},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"