mirror of
https://github.com/youronlydimwit/Data_ScienceUse_Cases.git
synced 2025-12-16 07:16:21 +01:00
795 lines
26 KiB
Plaintext
795 lines
26 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "5c3d106c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt \n",
|
|
"import seaborn as sns \n",
|
|
"import plotly as py\n",
|
|
"import os"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "7e7ad082",
|
|
"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>Id</th>\n",
|
|
" <th>SepalLengthCm</th>\n",
|
|
" <th>SepalWidthCm</th>\n",
|
|
" <th>PetalLengthCm</th>\n",
|
|
" <th>PetalWidthCm</th>\n",
|
|
" <th>Species</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>1</td>\n",
|
|
" <td>5.1</td>\n",
|
|
" <td>3.5</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>Iris-setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>2</td>\n",
|
|
" <td>4.9</td>\n",
|
|
" <td>3.0</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>Iris-setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>3</td>\n",
|
|
" <td>4.7</td>\n",
|
|
" <td>3.2</td>\n",
|
|
" <td>1.3</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>Iris-setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>4</td>\n",
|
|
" <td>4.6</td>\n",
|
|
" <td>3.1</td>\n",
|
|
" <td>1.5</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>Iris-setosa</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>5</td>\n",
|
|
" <td>5.0</td>\n",
|
|
" <td>3.6</td>\n",
|
|
" <td>1.4</td>\n",
|
|
" <td>0.2</td>\n",
|
|
" <td>Iris-setosa</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm Species\n",
|
|
"0 1 5.1 3.5 1.4 0.2 Iris-setosa\n",
|
|
"1 2 4.9 3.0 1.4 0.2 Iris-setosa\n",
|
|
"2 3 4.7 3.2 1.3 0.2 Iris-setosa\n",
|
|
"3 4 4.6 3.1 1.5 0.2 Iris-setosa\n",
|
|
"4 5 5.0 3.6 1.4 0.2 Iris-setosa"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df = pd.read_csv(r'D:\\archive\\iris.csv', encoding='utf-8')\n",
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "a85eca81",
|
|
"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>Id</th>\n",
|
|
" <th>SepalLengthCm</th>\n",
|
|
" <th>SepalWidthCm</th>\n",
|
|
" <th>PetalLengthCm</th>\n",
|
|
" <th>PetalWidthCm</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>count</th>\n",
|
|
" <td>150.000000</td>\n",
|
|
" <td>150.000000</td>\n",
|
|
" <td>150.000000</td>\n",
|
|
" <td>150.000000</td>\n",
|
|
" <td>150.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>mean</th>\n",
|
|
" <td>75.500000</td>\n",
|
|
" <td>5.843333</td>\n",
|
|
" <td>3.054000</td>\n",
|
|
" <td>3.758667</td>\n",
|
|
" <td>1.198667</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>std</th>\n",
|
|
" <td>43.445368</td>\n",
|
|
" <td>0.828066</td>\n",
|
|
" <td>0.433594</td>\n",
|
|
" <td>1.764420</td>\n",
|
|
" <td>0.763161</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>min</th>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>4.300000</td>\n",
|
|
" <td>2.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>0.100000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>25%</th>\n",
|
|
" <td>38.250000</td>\n",
|
|
" <td>5.100000</td>\n",
|
|
" <td>2.800000</td>\n",
|
|
" <td>1.600000</td>\n",
|
|
" <td>0.300000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>50%</th>\n",
|
|
" <td>75.500000</td>\n",
|
|
" <td>5.800000</td>\n",
|
|
" <td>3.000000</td>\n",
|
|
" <td>4.350000</td>\n",
|
|
" <td>1.300000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>75%</th>\n",
|
|
" <td>112.750000</td>\n",
|
|
" <td>6.400000</td>\n",
|
|
" <td>3.300000</td>\n",
|
|
" <td>5.100000</td>\n",
|
|
" <td>1.800000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>max</th>\n",
|
|
" <td>150.000000</td>\n",
|
|
" <td>7.900000</td>\n",
|
|
" <td>4.400000</td>\n",
|
|
" <td>6.900000</td>\n",
|
|
" <td>2.500000</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Id SepalLengthCm SepalWidthCm PetalLengthCm PetalWidthCm\n",
|
|
"count 150.000000 150.000000 150.000000 150.000000 150.000000\n",
|
|
"mean 75.500000 5.843333 3.054000 3.758667 1.198667\n",
|
|
"std 43.445368 0.828066 0.433594 1.764420 0.763161\n",
|
|
"min 1.000000 4.300000 2.000000 1.000000 0.100000\n",
|
|
"25% 38.250000 5.100000 2.800000 1.600000 0.300000\n",
|
|
"50% 75.500000 5.800000 3.000000 4.350000 1.300000\n",
|
|
"75% 112.750000 6.400000 3.300000 5.100000 1.800000\n",
|
|
"max 150.000000 7.900000 4.400000 6.900000 2.500000"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.describe()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "fd80a4a8",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Id int64\n",
|
|
"SepalLengthCm float64\n",
|
|
"SepalWidthCm float64\n",
|
|
"PetalLengthCm float64\n",
|
|
"PetalWidthCm float64\n",
|
|
"Species object\n",
|
|
"dtype: object"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.dtypes"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "cc10d9c3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import sklearn"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "d07459e2",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.metrics import confusion_matrix\n",
|
|
"from sklearn.model_selection import train_test_split"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "f917c7bd",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn import datasets"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "9d3e54c7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"iris = datasets.load_iris()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "1c34bd6d",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'data': array([[5.1, 3.5, 1.4, 0.2],\n",
|
|
" [4.9, 3. , 1.4, 0.2],\n",
|
|
" [4.7, 3.2, 1.3, 0.2],\n",
|
|
" [4.6, 3.1, 1.5, 0.2],\n",
|
|
" [5. , 3.6, 1.4, 0.2],\n",
|
|
" [5.4, 3.9, 1.7, 0.4],\n",
|
|
" [4.6, 3.4, 1.4, 0.3],\n",
|
|
" [5. , 3.4, 1.5, 0.2],\n",
|
|
" [4.4, 2.9, 1.4, 0.2],\n",
|
|
" [4.9, 3.1, 1.5, 0.1],\n",
|
|
" [5.4, 3.7, 1.5, 0.2],\n",
|
|
" [4.8, 3.4, 1.6, 0.2],\n",
|
|
" [4.8, 3. , 1.4, 0.1],\n",
|
|
" [4.3, 3. , 1.1, 0.1],\n",
|
|
" [5.8, 4. , 1.2, 0.2],\n",
|
|
" [5.7, 4.4, 1.5, 0.4],\n",
|
|
" [5.4, 3.9, 1.3, 0.4],\n",
|
|
" [5.1, 3.5, 1.4, 0.3],\n",
|
|
" [5.7, 3.8, 1.7, 0.3],\n",
|
|
" [5.1, 3.8, 1.5, 0.3],\n",
|
|
" [5.4, 3.4, 1.7, 0.2],\n",
|
|
" [5.1, 3.7, 1.5, 0.4],\n",
|
|
" [4.6, 3.6, 1. , 0.2],\n",
|
|
" [5.1, 3.3, 1.7, 0.5],\n",
|
|
" [4.8, 3.4, 1.9, 0.2],\n",
|
|
" [5. , 3. , 1.6, 0.2],\n",
|
|
" [5. , 3.4, 1.6, 0.4],\n",
|
|
" [5.2, 3.5, 1.5, 0.2],\n",
|
|
" [5.2, 3.4, 1.4, 0.2],\n",
|
|
" [4.7, 3.2, 1.6, 0.2],\n",
|
|
" [4.8, 3.1, 1.6, 0.2],\n",
|
|
" [5.4, 3.4, 1.5, 0.4],\n",
|
|
" [5.2, 4.1, 1.5, 0.1],\n",
|
|
" [5.5, 4.2, 1.4, 0.2],\n",
|
|
" [4.9, 3.1, 1.5, 0.2],\n",
|
|
" [5. , 3.2, 1.2, 0.2],\n",
|
|
" [5.5, 3.5, 1.3, 0.2],\n",
|
|
" [4.9, 3.6, 1.4, 0.1],\n",
|
|
" [4.4, 3. , 1.3, 0.2],\n",
|
|
" [5.1, 3.4, 1.5, 0.2],\n",
|
|
" [5. , 3.5, 1.3, 0.3],\n",
|
|
" [4.5, 2.3, 1.3, 0.3],\n",
|
|
" [4.4, 3.2, 1.3, 0.2],\n",
|
|
" [5. , 3.5, 1.6, 0.6],\n",
|
|
" [5.1, 3.8, 1.9, 0.4],\n",
|
|
" [4.8, 3. , 1.4, 0.3],\n",
|
|
" [5.1, 3.8, 1.6, 0.2],\n",
|
|
" [4.6, 3.2, 1.4, 0.2],\n",
|
|
" [5.3, 3.7, 1.5, 0.2],\n",
|
|
" [5. , 3.3, 1.4, 0.2],\n",
|
|
" [7. , 3.2, 4.7, 1.4],\n",
|
|
" [6.4, 3.2, 4.5, 1.5],\n",
|
|
" [6.9, 3.1, 4.9, 1.5],\n",
|
|
" [5.5, 2.3, 4. , 1.3],\n",
|
|
" [6.5, 2.8, 4.6, 1.5],\n",
|
|
" [5.7, 2.8, 4.5, 1.3],\n",
|
|
" [6.3, 3.3, 4.7, 1.6],\n",
|
|
" [4.9, 2.4, 3.3, 1. ],\n",
|
|
" [6.6, 2.9, 4.6, 1.3],\n",
|
|
" [5.2, 2.7, 3.9, 1.4],\n",
|
|
" [5. , 2. , 3.5, 1. ],\n",
|
|
" [5.9, 3. , 4.2, 1.5],\n",
|
|
" [6. , 2.2, 4. , 1. ],\n",
|
|
" [6.1, 2.9, 4.7, 1.4],\n",
|
|
" [5.6, 2.9, 3.6, 1.3],\n",
|
|
" [6.7, 3.1, 4.4, 1.4],\n",
|
|
" [5.6, 3. , 4.5, 1.5],\n",
|
|
" [5.8, 2.7, 4.1, 1. ],\n",
|
|
" [6.2, 2.2, 4.5, 1.5],\n",
|
|
" [5.6, 2.5, 3.9, 1.1],\n",
|
|
" [5.9, 3.2, 4.8, 1.8],\n",
|
|
" [6.1, 2.8, 4. , 1.3],\n",
|
|
" [6.3, 2.5, 4.9, 1.5],\n",
|
|
" [6.1, 2.8, 4.7, 1.2],\n",
|
|
" [6.4, 2.9, 4.3, 1.3],\n",
|
|
" [6.6, 3. , 4.4, 1.4],\n",
|
|
" [6.8, 2.8, 4.8, 1.4],\n",
|
|
" [6.7, 3. , 5. , 1.7],\n",
|
|
" [6. , 2.9, 4.5, 1.5],\n",
|
|
" [5.7, 2.6, 3.5, 1. ],\n",
|
|
" [5.5, 2.4, 3.8, 1.1],\n",
|
|
" [5.5, 2.4, 3.7, 1. ],\n",
|
|
" [5.8, 2.7, 3.9, 1.2],\n",
|
|
" [6. , 2.7, 5.1, 1.6],\n",
|
|
" [5.4, 3. , 4.5, 1.5],\n",
|
|
" [6. , 3.4, 4.5, 1.6],\n",
|
|
" [6.7, 3.1, 4.7, 1.5],\n",
|
|
" [6.3, 2.3, 4.4, 1.3],\n",
|
|
" [5.6, 3. , 4.1, 1.3],\n",
|
|
" [5.5, 2.5, 4. , 1.3],\n",
|
|
" [5.5, 2.6, 4.4, 1.2],\n",
|
|
" [6.1, 3. , 4.6, 1.4],\n",
|
|
" [5.8, 2.6, 4. , 1.2],\n",
|
|
" [5. , 2.3, 3.3, 1. ],\n",
|
|
" [5.6, 2.7, 4.2, 1.3],\n",
|
|
" [5.7, 3. , 4.2, 1.2],\n",
|
|
" [5.7, 2.9, 4.2, 1.3],\n",
|
|
" [6.2, 2.9, 4.3, 1.3],\n",
|
|
" [5.1, 2.5, 3. , 1.1],\n",
|
|
" [5.7, 2.8, 4.1, 1.3],\n",
|
|
" [6.3, 3.3, 6. , 2.5],\n",
|
|
" [5.8, 2.7, 5.1, 1.9],\n",
|
|
" [7.1, 3. , 5.9, 2.1],\n",
|
|
" [6.3, 2.9, 5.6, 1.8],\n",
|
|
" [6.5, 3. , 5.8, 2.2],\n",
|
|
" [7.6, 3. , 6.6, 2.1],\n",
|
|
" [4.9, 2.5, 4.5, 1.7],\n",
|
|
" [7.3, 2.9, 6.3, 1.8],\n",
|
|
" [6.7, 2.5, 5.8, 1.8],\n",
|
|
" [7.2, 3.6, 6.1, 2.5],\n",
|
|
" [6.5, 3.2, 5.1, 2. ],\n",
|
|
" [6.4, 2.7, 5.3, 1.9],\n",
|
|
" [6.8, 3. , 5.5, 2.1],\n",
|
|
" [5.7, 2.5, 5. , 2. ],\n",
|
|
" [5.8, 2.8, 5.1, 2.4],\n",
|
|
" [6.4, 3.2, 5.3, 2.3],\n",
|
|
" [6.5, 3. , 5.5, 1.8],\n",
|
|
" [7.7, 3.8, 6.7, 2.2],\n",
|
|
" [7.7, 2.6, 6.9, 2.3],\n",
|
|
" [6. , 2.2, 5. , 1.5],\n",
|
|
" [6.9, 3.2, 5.7, 2.3],\n",
|
|
" [5.6, 2.8, 4.9, 2. ],\n",
|
|
" [7.7, 2.8, 6.7, 2. ],\n",
|
|
" [6.3, 2.7, 4.9, 1.8],\n",
|
|
" [6.7, 3.3, 5.7, 2.1],\n",
|
|
" [7.2, 3.2, 6. , 1.8],\n",
|
|
" [6.2, 2.8, 4.8, 1.8],\n",
|
|
" [6.1, 3. , 4.9, 1.8],\n",
|
|
" [6.4, 2.8, 5.6, 2.1],\n",
|
|
" [7.2, 3. , 5.8, 1.6],\n",
|
|
" [7.4, 2.8, 6.1, 1.9],\n",
|
|
" [7.9, 3.8, 6.4, 2. ],\n",
|
|
" [6.4, 2.8, 5.6, 2.2],\n",
|
|
" [6.3, 2.8, 5.1, 1.5],\n",
|
|
" [6.1, 2.6, 5.6, 1.4],\n",
|
|
" [7.7, 3. , 6.1, 2.3],\n",
|
|
" [6.3, 3.4, 5.6, 2.4],\n",
|
|
" [6.4, 3.1, 5.5, 1.8],\n",
|
|
" [6. , 3. , 4.8, 1.8],\n",
|
|
" [6.9, 3.1, 5.4, 2.1],\n",
|
|
" [6.7, 3.1, 5.6, 2.4],\n",
|
|
" [6.9, 3.1, 5.1, 2.3],\n",
|
|
" [5.8, 2.7, 5.1, 1.9],\n",
|
|
" [6.8, 3.2, 5.9, 2.3],\n",
|
|
" [6.7, 3.3, 5.7, 2.5],\n",
|
|
" [6.7, 3. , 5.2, 2.3],\n",
|
|
" [6.3, 2.5, 5. , 1.9],\n",
|
|
" [6.5, 3. , 5.2, 2. ],\n",
|
|
" [6.2, 3.4, 5.4, 2.3],\n",
|
|
" [5.9, 3. , 5.1, 1.8]]),\n",
|
|
" 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
|
|
" 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
|
|
" 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
|
|
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
|
|
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
|
|
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
|
|
" 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
|
|
" 'frame': None,\n",
|
|
" 'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),\n",
|
|
" 'DESCR': '.. _iris_dataset:\\n\\nIris plants dataset\\n--------------------\\n\\n**Data Set Characteristics:**\\n\\n :Number of Instances: 150 (50 in each of three classes)\\n :Number of Attributes: 4 numeric, predictive attributes and the class\\n :Attribute Information:\\n - sepal length in cm\\n - sepal width in cm\\n - petal length in cm\\n - petal width in cm\\n - class:\\n - Iris-Setosa\\n - Iris-Versicolour\\n - Iris-Virginica\\n \\n :Summary Statistics:\\n\\n ============== ==== ==== ======= ===== ====================\\n Min Max Mean SD Class Correlation\\n ============== ==== ==== ======= ===== ====================\\n sepal length: 4.3 7.9 5.84 0.83 0.7826\\n sepal width: 2.0 4.4 3.05 0.43 -0.4194\\n petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)\\n petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)\\n ============== ==== ==== ======= ===== ====================\\n\\n :Missing Attribute Values: None\\n :Class Distribution: 33.3% for each of 3 classes.\\n :Creator: R.A. Fisher\\n :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\\n :Date: July, 1988\\n\\nThe famous Iris database, first used by Sir R.A. Fisher. The dataset is taken\\nfrom Fisher\\'s paper. Note that it\\'s the same as in R, but not as in the UCI\\nMachine Learning Repository, which has two wrong data points.\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature. Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day. (See Duda & Hart, for example.) The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant. One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\n.. topic:: References\\n\\n - Fisher, R.A. \"The use of multiple measurements in taxonomic problems\"\\n Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\\n Mathematical Statistics\" (John Wiley, NY, 1950).\\n - Duda, R.O., & Hart, P.E. (1973) Pattern Classification and Scene Analysis.\\n (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.\\n - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\\n Structure and Classification Rule for Recognition in Partially Exposed\\n Environments\". IEEE Transactions on Pattern Analysis and Machine\\n Intelligence, Vol. PAMI-2, No. 1, 67-71.\\n - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\". IEEE Transactions\\n on Information Theory, May 1972, 431-433.\\n - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al\"s AUTOCLASS II\\n conceptual clustering system finds 3 classes in the data.\\n - Many, many more ...',\n",
|
|
" 'feature_names': ['sepal length (cm)',\n",
|
|
" 'sepal width (cm)',\n",
|
|
" 'petal length (cm)',\n",
|
|
" 'petal width (cm)'],\n",
|
|
" 'filename': 'iris.csv',\n",
|
|
" 'data_module': 'sklearn.datasets.data'}"
|
|
]
|
|
},
|
|
"execution_count": 12,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"iris"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"id": "606f7821",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"X = df.iloc[:,:-1]\n",
|
|
"y = df.iloc[:,-1]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"id": "4f7dade3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"X_train, X_test, y_train, y_test = train_test_split(X,y,random_state=0)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"id": "85c8563e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from sklearn.tree import DecisionTreeClassifier\n",
|
|
"from sklearn.svm import SVC\n",
|
|
"from sklearn.neighbors import KNeighborsClassifier\n",
|
|
"from sklearn.naive_bayes import GaussianNB"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 18,
|
|
"id": "da7a7529",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"['Iris-virginica' 'Iris-versicolor' 'Iris-setosa' 'Iris-virginica'\n",
|
|
" 'Iris-setosa' 'Iris-versicolor' 'Iris-setosa' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-versicolor' 'Iris-setosa'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-setosa' 'Iris-setosa'\n",
|
|
" 'Iris-virginica' 'Iris-versicolor' 'Iris-setosa' 'Iris-setosa'\n",
|
|
" 'Iris-virginica' 'Iris-setosa' 'Iris-setosa' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-setosa' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-setosa' 'Iris-virginica' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-setosa' 'Iris-versicolor']\n",
|
|
"[[13 0 0]\n",
|
|
" [ 0 16 0]\n",
|
|
" [ 0 1 8]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"dtree = DecisionTreeClassifier(max_depth = 2).fit(X_train, y_train)\n",
|
|
"dtree_pred = dtree.predict(X_test)\n",
|
|
"#confusionmatrix\n",
|
|
"cf = confusion_matrix(y_test,dtree_pred)\n",
|
|
"print(dtree_pred)\n",
|
|
"print(cf)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"id": "17682b48",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"0.9736842105263158"
|
|
]
|
|
},
|
|
"execution_count": 24,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"dtree.score(X_test,y_test)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 26,
|
|
"id": "4f4d6dc0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"svm_mod = SVC(kernel='linear',C=1).fit(X_train, y_train)\n",
|
|
"svm_pred= svm_mod.predict(X_test)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 31,
|
|
"id": "a2280e55",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"1.0\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"accsvm=svm_mod.score(X_test, svm_pred)\n",
|
|
"print(accsvm)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 40,
|
|
"id": "798a5c23",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[[13 0 0]\n",
|
|
" [ 0 16 0]\n",
|
|
" [ 0 0 9]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"svmc = confusion_matrix(y_test, svm_pred)\n",
|
|
"print(svmc)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 33,
|
|
"id": "ae7a988b",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"knn=KNeighborsClassifier(n_neighbors=7).fit(X_train,y_train)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 35,
|
|
"id": "2fa42653",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"1.0\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"accknn=knn.score(X_test,y_test)\n",
|
|
"print(accknn)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 37,
|
|
"id": "f801cbdf",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"['Iris-virginica' 'Iris-versicolor' 'Iris-setosa' 'Iris-virginica'\n",
|
|
" 'Iris-setosa' 'Iris-virginica' 'Iris-setosa' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-versicolor' 'Iris-setosa'\n",
|
|
" 'Iris-versicolor' 'Iris-versicolor' 'Iris-setosa' 'Iris-setosa'\n",
|
|
" 'Iris-virginica' 'Iris-versicolor' 'Iris-setosa' 'Iris-setosa'\n",
|
|
" 'Iris-virginica' 'Iris-setosa' 'Iris-setosa' 'Iris-versicolor'\n",
|
|
" 'Iris-versicolor' 'Iris-setosa' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-setosa' 'Iris-virginica' 'Iris-virginica' 'Iris-versicolor'\n",
|
|
" 'Iris-setosa' 'Iris-versicolor']\n",
|
|
"[[13 0 0]\n",
|
|
" [ 0 16 0]\n",
|
|
" [ 0 0 9]]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"knn_pred = knn.predict(X_test)\n",
|
|
"cm = confusion_matrix(y_test, knn_pred)\n",
|
|
"print(knn_pred)\n",
|
|
"print(cm)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 42,
|
|
"id": "17a6e503",
|
|
"metadata": {
|
|
"scrolled": true
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"114 Iris-virginica\n",
|
|
"62 Iris-versicolor\n",
|
|
"33 Iris-setosa\n",
|
|
"107 Iris-virginica\n",
|
|
"7 Iris-setosa\n",
|
|
"100 Iris-virginica\n",
|
|
"40 Iris-setosa\n",
|
|
"86 Iris-versicolor\n",
|
|
"76 Iris-versicolor\n",
|
|
"71 Iris-versicolor\n",
|
|
"134 Iris-virginica\n",
|
|
"51 Iris-versicolor\n",
|
|
"73 Iris-versicolor\n",
|
|
"54 Iris-versicolor\n",
|
|
"63 Iris-versicolor\n",
|
|
"37 Iris-setosa\n",
|
|
"78 Iris-versicolor\n",
|
|
"90 Iris-versicolor\n",
|
|
"45 Iris-setosa\n",
|
|
"16 Iris-setosa\n",
|
|
"121 Iris-virginica\n",
|
|
"66 Iris-versicolor\n",
|
|
"24 Iris-setosa\n",
|
|
"8 Iris-setosa\n",
|
|
"126 Iris-virginica\n",
|
|
"22 Iris-setosa\n",
|
|
"44 Iris-setosa\n",
|
|
"97 Iris-versicolor\n",
|
|
"93 Iris-versicolor\n",
|
|
"26 Iris-setosa\n",
|
|
"137 Iris-virginica\n",
|
|
"84 Iris-versicolor\n",
|
|
"27 Iris-setosa\n",
|
|
"127 Iris-virginica\n",
|
|
"132 Iris-virginica\n",
|
|
"59 Iris-versicolor\n",
|
|
"18 Iris-setosa\n",
|
|
"83 Iris-versicolor\n",
|
|
"Name: Species, dtype: object"
|
|
]
|
|
},
|
|
"execution_count": 42,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"y_test"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "72e4ee91",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"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": "3.9.12"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|