{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Machine Learing For Oracle Professionals"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Latest: 6-Jan-2020 v1b"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Congratuations on entering our learning environment!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "x=\"hello new world once again\"\n",
    "print(x)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load all the libraries needed for this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np   # To do array and math stuff\n",
    "import pandas as pd  # To do dataframe and math stuff\n",
    "import matplotlib    # To do plots\n",
    "from matplotlib import pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are many ways to load data into our workspace.\n",
    "First, read a CSV file directly from a URL."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"http://filebank.orapub.com/DataSets/ml-setup-demo-data.csv\"\n",
    "features = pd.read_csv(url, nrows=0).columns.tolist() # read the first row, which contains the column/feature names\n",
    "features = [x.strip(' ') for x in features] # remove leading/trailing spaces\n",
    "print(features) # display the data columns/features\n",
    "dfraw = pd.read_csv(url, names=features, skiprows=1)  # read CSV contents from the URL, into the dataframe, dfraw"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For now, let's just print the structure, the column headings and a few rows."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfraw.shape  # (rows, columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfraw.columns  # show all dataframe columns/features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dfraw.head()  # display the first few dataframe rows"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's save the dfraw dataframe to your desktop as a CSV file."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Modify the below path to point to your desktop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "export_csv = dfraw.to_csv ('/Users/cshallah/Desktop/testdata.csv', index=None, header=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's check to see if the file is on your Desktop, by re-reading the CSV file into a new dataframe, mydf."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mydf = pd.read_csv('/Users/cshallah/Desktop/testdata.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "mydf.head(4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load some of the ML libraries needed for OraPub's Machine Learning classes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os            # To access your local OS\n",
    "import pickle        # file IO\n",
    "\n",
    "from sklearn import preprocessing\n",
    "from sklearn.model_selection import train_test_split\n",
    "from datetime import datetime, timedelta \n",
    "from sklearn.preprocessing import LabelBinarizer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import classification_report\n",
    "from matplotlib import pyplot as plt\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.dummy import DummyClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.datasets import make_classification # needed with RandomForestClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn import tree\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.svm import SVC, LinearSVC\n",
    "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "\n",
    "print(\"Done.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}