Skip to content

D
DM-Project
Commit 91bfa09b authored by Almouhannad's avatar Almouhannad
Browse files
Options

Add algorithms

parent fb8fcf89
Hide whitespace changes
Inline Side-by-side
Showing with 658 additions and 17 deletions
.gitignore
View file @ 91bfa09b
__pycache__/constants.cpython-311.pyc
data/bread_basket_preprocessed.csv
constants.py
View file @ 91bfa09b
......@@ -2,4 +2,6 @@ class CONSTANTS:
DATASET_PATH = 'data/bread_basket.csv'
DATASET_SHAPE = (20507, 5)
PREPROCESSED_DATASET_PATH = 'data/bread_basket_preprocessed.csv'
PREPROCESSED_DATASET_SHAPE = (9465, 94)
\ No newline at end of file
PREPROCESSED_DATASET_SHAPE = (9465, 94)
MIN_SUPPORT_VALUE = 0.2 # Adjust this value based on problem
MIN_CONFIDENCE_VALUE = 0.5 # Adjust this value based on problem
\ No newline at end of file
hw1.ipynb
View file @ 91bfa09b
......@@ -33,9 +33,21 @@
"import pandas as pd\n",
"\n",
"from mlxtend.frequent_patterns import apriori, association_rules\n",
"from mlxtend.frequent_patterns import fpgrowth\n",
"\n",
"from constants import CONSTANTS"
"from mlxtend.frequent_patterns import fpgrowth"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from constants import CONSTANTS\n",
"# Some more magic so that the notebook will reload external python modules;\n",
"# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython\n",
"%load_ext autoreload\n",
"%autoreload 2\n",
"%reload_ext autoreload"
]
},
{
......@@ -54,7 +66,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 4,
"metadata": {},
"outputs": [
{
......@@ -81,7 +93,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 5,
"metadata": {},
"outputs": [
{
......@@ -119,7 +131,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 6,
"metadata": {},
"outputs": [
{
......@@ -143,7 +155,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 7,
"metadata": {},
"outputs": [
{
......@@ -170,7 +182,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 8,
"metadata": {},
"outputs": [
{
......@@ -196,7 +208,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 9,
"metadata": {},
"outputs": [
{
......@@ -236,7 +248,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 10,
"metadata": {},
"outputs": [
{
......@@ -281,7 +293,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 11,
"metadata": {},
"outputs": [
{
......@@ -355,7 +367,7 @@
"5 3 Cookies"
]
},
"execution_count": 10,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
......@@ -367,7 +379,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 12,
"metadata": {},
"outputs": [
{
......@@ -394,7 +406,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 13,
"metadata": {},
"outputs": [
{
......@@ -436,11 +448,13 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv(CONSTANTS.PREPROCESSED_DATASET_PATH)"
"df.to_csv(CONSTANTS.PREPROCESSED_DATASET_PATH, index=False)\n",
"# Free memory\n",
"df = None"
]
},
{
......@@ -450,6 +464,318 @@
"# ***2. Extracting rules using Apriori***"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***2.1. Load dataset***"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset loaded successfully\n"
]
}
],
"source": [
"df = None\n",
"df = pd.read_csv(CONSTANTS.PREPROCESSED_DATASET_PATH)\n",
"assert df.shape == CONSTANTS.PREPROCESSED_DATASET_SHAPE, f\"Expected shape {CONSTANTS.PREPROCESSED_DATASET_SHAPE}, but got {df.shape}\" \n",
"print(f\"Dataset loaded successfully\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**We'll deal only with first 15 transactions**"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"df = df.head(15)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***2.2. Get repeated item sets***"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Repeated item sets using Apriori with min_support = 0.2:\n"
]
},
{
"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>support</th>\n",
" <th>itemsets</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.466667</td>\n",
" <td>(Bread)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.266667</td>\n",
" <td>(Coffee)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.333333</td>\n",
" <td>(Medialuna)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.200000</td>\n",
" <td>(Muffin)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.400000</td>\n",
" <td>(Pastry)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.200000</td>\n",
" <td>(Scandinavian)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.200000</td>\n",
" <td>(Pastry, Bread)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.200000</td>\n",
" <td>(Coffee, Pastry)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0.200000</td>\n",
" <td>(Pastry, Medialuna)</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" support itemsets\n",
"0 0.466667 (Bread)\n",
"1 0.266667 (Coffee)\n",
"2 0.333333 (Medialuna)\n",
"3 0.200000 (Muffin)\n",
"4 0.400000 (Pastry)\n",
"5 0.200000 (Scandinavian)\n",
"6 0.200000 (Pastry, Bread)\n",
"7 0.200000 (Coffee, Pastry)\n",
"8 0.200000 (Pastry, Medialuna)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"min_support = CONSTANTS.MIN_SUPPORT_VALUE\n",
"repeated_item_sets_apriori = apriori(df, min_support=min_support, use_colnames=True)\n",
"print(f\"Repeated item sets using Apriori with min_support = {min_support}:\")\n",
"repeated_item_sets_apriori"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***2.3. Get rules***"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Association rules using Apriori with min_support = 0.2 and min_confidence = 0.5:\n"
]
},
{
"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>antecedents</th>\n",
" <th>consequents</th>\n",
" <th>antecedent support</th>\n",
" <th>consequent support</th>\n",
" <th>support</th>\n",
" <th>confidence</th>\n",
" <th>lift</th>\n",
" <th>leverage</th>\n",
" <th>conviction</th>\n",
" <th>zhangs_metric</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Bread)</td>\n",
" <td>0.400000</td>\n",
" <td>0.466667</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.071429</td>\n",
" <td>0.013333</td>\n",
" <td>1.066667</td>\n",
" <td>0.111111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>(Coffee)</td>\n",
" <td>(Pastry)</td>\n",
" <td>0.266667</td>\n",
" <td>0.400000</td>\n",
" <td>0.2</td>\n",
" <td>0.75</td>\n",
" <td>1.875000</td>\n",
" <td>0.093333</td>\n",
" <td>2.400000</td>\n",
" <td>0.636364</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Coffee)</td>\n",
" <td>0.400000</td>\n",
" <td>0.266667</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.875000</td>\n",
" <td>0.093333</td>\n",
" <td>1.466667</td>\n",
" <td>0.777778</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Medialuna)</td>\n",
" <td>0.400000</td>\n",
" <td>0.333333</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.500000</td>\n",
" <td>0.066667</td>\n",
" <td>1.333333</td>\n",
" <td>0.555556</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>(Medialuna)</td>\n",
" <td>(Pastry)</td>\n",
" <td>0.333333</td>\n",
" <td>0.400000</td>\n",
" <td>0.2</td>\n",
" <td>0.60</td>\n",
" <td>1.500000</td>\n",
" <td>0.066667</td>\n",
" <td>1.500000</td>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" antecedents consequents antecedent support consequent support support \\\n",
"0 (Pastry) (Bread) 0.400000 0.466667 0.2 \n",
"1 (Coffee) (Pastry) 0.266667 0.400000 0.2 \n",
"2 (Pastry) (Coffee) 0.400000 0.266667 0.2 \n",
"3 (Pastry) (Medialuna) 0.400000 0.333333 0.2 \n",
"4 (Medialuna) (Pastry) 0.333333 0.400000 0.2 \n",
"\n",
" confidence lift leverage conviction zhangs_metric \n",
"0 0.50 1.071429 0.013333 1.066667 0.111111 \n",
"1 0.75 1.875000 0.093333 2.400000 0.636364 \n",
"2 0.50 1.875000 0.093333 1.466667 0.777778 \n",
"3 0.50 1.500000 0.066667 1.333333 0.555556 \n",
"4 0.60 1.500000 0.066667 1.500000 0.500000 "
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"min_confidence = CONSTANTS.MIN_CONFIDENCE_VALUE\n",
"rules_apriori = association_rules(repeated_item_sets_apriori, metric=\"confidence\", min_threshold=min_confidence)\n",
"print(f\"Association rules using Apriori with min_support = {min_support} and min_confidence = {min_confidence}:\")\n",
"rules_apriori"
]
},
{
"cell_type": "markdown",
"metadata": {},
......@@ -457,6 +783,318 @@
"# ***3. Extracting rules using FP Growth***"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***3.1. Load dataset***"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dataset loaded successfully\n"
]
}
],
"source": [
"df = None\n",
"df = pd.read_csv(CONSTANTS.PREPROCESSED_DATASET_PATH)\n",
"assert df.shape == CONSTANTS.PREPROCESSED_DATASET_SHAPE, f\"Expected shape {CONSTANTS.PREPROCESSED_DATASET_SHAPE}, but got {df.shape}\" \n",
"print(f\"Dataset loaded successfully\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**We'll deal only with first 15 transactions**"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"df = df.head(15)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***3.2. Get repeated item sets***\n"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Repeated item sets using FP Growth with min_support = 0.2:\n"
]
},
{
"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>support</th>\n",
" <th>itemsets</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.466667</td>\n",
" <td>(Bread)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.200000</td>\n",
" <td>(Scandinavian)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.200000</td>\n",
" <td>(Muffin)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.400000</td>\n",
" <td>(Pastry)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.266667</td>\n",
" <td>(Coffee)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.333333</td>\n",
" <td>(Medialuna)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.200000</td>\n",
" <td>(Pastry, Bread)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.200000</td>\n",
" <td>(Coffee, Pastry)</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0.200000</td>\n",
" <td>(Pastry, Medialuna)</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" support itemsets\n",
"0 0.466667 (Bread)\n",
"1 0.200000 (Scandinavian)\n",
"2 0.200000 (Muffin)\n",
"3 0.400000 (Pastry)\n",
"4 0.266667 (Coffee)\n",
"5 0.333333 (Medialuna)\n",
"6 0.200000 (Pastry, Bread)\n",
"7 0.200000 (Coffee, Pastry)\n",
"8 0.200000 (Pastry, Medialuna)"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"min_support = CONSTANTS.MIN_SUPPORT_VALUE\n",
"repeated_item_sets_fpg = fpgrowth(df, min_support=min_support, use_colnames=True)\n",
"print(f\"Repeated item sets using FP Growth with min_support = {min_support}:\")\n",
"repeated_item_sets_fpg"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ***3.3. Get rules***\n"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Association rules using FP Growth with min_support = 0.2 and min_confidence = 0.5:\n"
]
},
{
"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>antecedents</th>\n",
" <th>consequents</th>\n",
" <th>antecedent support</th>\n",
" <th>consequent support</th>\n",
" <th>support</th>\n",
" <th>confidence</th>\n",
" <th>lift</th>\n",
" <th>leverage</th>\n",
" <th>conviction</th>\n",
" <th>zhangs_metric</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Bread)</td>\n",
" <td>0.400000</td>\n",
" <td>0.466667</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.071429</td>\n",
" <td>0.013333</td>\n",
" <td>1.066667</td>\n",
" <td>0.111111</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>(Coffee)</td>\n",
" <td>(Pastry)</td>\n",
" <td>0.266667</td>\n",
" <td>0.400000</td>\n",
" <td>0.2</td>\n",
" <td>0.75</td>\n",
" <td>1.875000</td>\n",
" <td>0.093333</td>\n",
" <td>2.400000</td>\n",
" <td>0.636364</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Coffee)</td>\n",
" <td>0.400000</td>\n",
" <td>0.266667</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.875000</td>\n",
" <td>0.093333</td>\n",
" <td>1.466667</td>\n",
" <td>0.777778</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>(Pastry)</td>\n",
" <td>(Medialuna)</td>\n",
" <td>0.400000</td>\n",
" <td>0.333333</td>\n",
" <td>0.2</td>\n",
" <td>0.50</td>\n",
" <td>1.500000</td>\n",
" <td>0.066667</td>\n",
" <td>1.333333</td>\n",
" <td>0.555556</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>(Medialuna)</td>\n",
" <td>(Pastry)</td>\n",
" <td>0.333333</td>\n",
" <td>0.400000</td>\n",
" <td>0.2</td>\n",
" <td>0.60</td>\n",
" <td>1.500000</td>\n",
" <td>0.066667</td>\n",
" <td>1.500000</td>\n",
" <td>0.500000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" antecedents consequents antecedent support consequent support support \\\n",
"0 (Pastry) (Bread) 0.400000 0.466667 0.2 \n",
"1 (Coffee) (Pastry) 0.266667 0.400000 0.2 \n",
"2 (Pastry) (Coffee) 0.400000 0.266667 0.2 \n",
"3 (Pastry) (Medialuna) 0.400000 0.333333 0.2 \n",
"4 (Medialuna) (Pastry) 0.333333 0.400000 0.2 \n",
"\n",
" confidence lift leverage conviction zhangs_metric \n",
"0 0.50 1.071429 0.013333 1.066667 0.111111 \n",
"1 0.75 1.875000 0.093333 2.400000 0.636364 \n",
"2 0.50 1.875000 0.093333 1.466667 0.777778 \n",
"3 0.50 1.500000 0.066667 1.333333 0.555556 \n",
"4 0.60 1.500000 0.066667 1.500000 0.500000 "
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"min_confidence = CONSTANTS.MIN_CONFIDENCE_VALUE\n",
"rules_fpg = association_rules(repeated_item_sets_apriori, metric=\"confidence\", min_threshold=min_confidence)\n",
"print(f\"Association rules using FP Growth with min_support = {min_support} and min_confidence = {min_confidence}:\")\n",
"rules_fpg"
]
},
{
"cell_type": "markdown",
"metadata": {},
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment

HIAST - GitLab