\n",
" \n",
" | 0 | \n",
- " {'C': 10.0, 'max_iter': 1000} | \n",
- " 0.999110 | \n",
+ " {'C': 0.1, 'max_iter': 100} | \n",
+ " 0.999155 | \n",
"
\n",
" \n",
" | 1 | \n",
- " {'C': 0.1, 'max_iter': 1000} | \n",
- " 0.999095 | \n",
+ " {'C': 0.1, 'max_iter': 500} | \n",
+ " 0.999155 | \n",
"
\n",
" \n",
" | 2 | \n",
- " {'C': 1.0, 'max_iter': 1000} | \n",
- " 0.999095 | \n",
+ " {'C': 0.1, 'max_iter': 1000} | \n",
+ " 0.999155 | \n",
"
\n",
" \n",
" | 3 | \n",
- " {'C': 10.0, 'max_iter': 100} | \n",
- " 0.998989 | \n",
+ " {'C': 1, 'max_iter': 100} | \n",
+ " 0.999155 | \n",
"
\n",
" \n",
" | 4 | \n",
- " {'C': 0.1, 'max_iter': 100} | \n",
- " 0.998884 | \n",
+ " {'C': 1, 'max_iter': 500} | \n",
+ " 0.999155 | \n",
"
\n",
" \n",
"\n",
""
],
"text/plain": [
- " Parameters accuracy\n",
- "0 {'C': 10.0, 'max_iter': 1000} 0.999110\n",
- "1 {'C': 0.1, 'max_iter': 1000} 0.999095\n",
- "2 {'C': 1.0, 'max_iter': 1000} 0.999095\n",
- "3 {'C': 10.0, 'max_iter': 100} 0.998989\n",
- "4 {'C': 0.1, 'max_iter': 100} 0.998884"
+ " Parameters f1\n",
+ "0 {'C': 0.1, 'max_iter': 100} 0.999155\n",
+ "1 {'C': 0.1, 'max_iter': 500} 0.999155\n",
+ "2 {'C': 0.1, 'max_iter': 1000} 0.999155\n",
+ "3 {'C': 1, 'max_iter': 100} 0.999155\n",
+ "4 {'C': 1, 'max_iter': 500} 0.999155"
]
},
- "execution_count": 24,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
- "#import warnings\n",
- "#\n",
- "# warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)\n",
+ "hyperparameters = {\"C\":[0.1,1,10],\"max_iter\":[100,500,1000]}\n",
+ "results = grid_search(logistic_regression,hyperparameters,\"f1\",X_train,X_test,y_train,y_test)\n",
+ "results.head()\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Model Coefficients: [[ 0.02520122 0.00417009 0.04143354 -0.10483769 0.10516741 0.08317194\n",
+ " 0.00119811]]\n",
+ "Model Intercept: [0.00554605]\n",
+ "Model Score: [0 0 0 ... 0 1 0]\n",
+ "Confusion Matrix: [[39351 56]\n",
+ " [ 0 26886]]\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "0.9989596492531768"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "logistic_regression(X_train,X_test,y_train,y_test,metric=\"f1\",verbose=True,C=0.1,max_iter=500)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def decision_tree(X_train,X_test,y_train,y_test,metric=\"accuracy\",verbose=False):\n",
+ " from sklearn.tree import DecisionTreeClassifier\n",
+ " \"\"\"\n",
+ " This function performs logistic regression on the data and returns the accuracy of the model\n",
+ " Necessary Arguments:\n",
+ " X_train : The training data\n",
+ " X_test : The test data\n",
+ " y_train : The target values\n",
+ " y_test : The target values for the training data\n",
"\n",
- "hyperparameters = {\"C\":[0.1,1.0,10.0],\"max_iter\":[10,100,1000]}\n",
- "results = grid_search(logistic_regression,hyperparameters,\"accuracy\",X_train,X_test,y_train,y_test)\n",
+ " Optional Arguments:\n",
+ " metric : The metric to calculate the model performance, Options: \"accuracy\", \"precision\", \"recall\", \"f1\"\n",
+ " verbose : If True, the function will print the metric of the model\n",
"\n",
- "results.head()\n"
+ " Returns:\n",
+ " metric_value : The number of the metric specified in the arguments\n",
+ " \"\"\"\n",
+ "\n",
+ " # create a decision tree model\n",
+ " model = DecisionTreeClassifier()\n",
+ "\n",
+ " # fit the model to the training data\n",
+ " model.fit(X_train, y_train)\n",
+ "\n",
+ " # predict the target values for the test data\n",
+ " y_pred = model.predict(X_test)\n",
+ "\n",
+ " if verbose==True:\n",
+ " print(f\"Model Score: {y_pred}\")\n",
+ " cm = confusion_matrix(y_test, y_pred)\n",
+ " disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=data.target_names)\n",
+ " disp.plot()\n",
+ "\n",
+ " metric_value = 0\n",
+ " # calculate the metric of the model\n",
+ " if metric == \"accuracy\":\n",
+ " metric_value = accuracy_score(y_test, y_pred)\n",
+ " if metric == \"precision\":\n",
+ " metric_value = precision_score(y_test, y_pred)\n",
+ " if metric == \"recall\":\n",
+ " metric_value = recall_score(y_test, y_pred)\n",
+ " if metric == \"f1\":\n",
+ " metric_value = f1_score(y_test, y_pred)\n",
+ " return metric_value"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def xgb(X_train,X_test,y_train,y_test,metric=\"accuracy\",booster=\"gbtree\",eta=0.3,max_depth=6, reg_lambda=1, verbose=False):\n",
+ "\n",
+ " \"\"\"\n",
+ " This function performs xgboost on the data and returns the accuracy of the model\n",
+ " Necessary Arguments:\n",
+ " X_train : The training data\n",
+ " X_test : The test data\n",
+ " y_train : The target values\n",
+ " y_test : The target values for the training data\n",
+ "\n",
+ " Optional Arguments:\n",
+ " metric : The metric to calculate the model performance, Options: \"accuracy\", \"precision\", \"recall\", \"f1\"\n",
+ " verbose : If True, the function will print the metric of the model\n",
+ " booster : The type of booster to use, Options: \"gbtree\", \"gblinear\", \"dart\"\n",
+ " eta : The learning rate of the model, between [0,1]\n",
+ " max_depth : The maximum depth of the trees, default is 6 to avoid overfitting\n",
+ " reg_lambda : The regularization parameter of the model\n",
+ "\n",
+ " Returns:\n",
+ " metric_value : The number of the metric specified in the arguments\n",
+ " \"\"\"\n",
+ " from xgboost import XGBClassifier\n",
+ " # create a logistic regression model\n",
+ " model = XGBClassifier(booster=booster,eta=eta)\n",
+ "\n",
+ " # fit the model to the training data\n",
+ " model.fit(X_train, y_train)\n",
+ "\n",
+ " # predict the target values for the test data\n",
+ " y_pred = model.predict(X_test)\n",
+ "\n",
+ " if verbose==True:\n",
+ " print(f\"Model Score: {y_pred}\")\n",
+ " cm = confusion_matrix(y_test, y_pred)\n",
+ " disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=data.target_names)\n",
+ " disp.plot()\n",
+ " \n",
+ "\n",
+ " metric_value = 0\n",
+ " # calculate the metric of the model\n",
+ " if metric == \"accuracy\":\n",
+ " metric_value = accuracy_score(y_test, y_pred)\n",
+ " if metric == \"precision\":\n",
+ " metric_value = precision_score(y_test, y_pred)\n",
+ " if metric == \"recall\":\n",
+ " metric_value = recall_score(y_test, y_pred)\n",
+ " if metric == \"f1\":\n",
+ " metric_value = f1_score(y_test, y_pred)\n",
+ " return metric_value"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data,transform_data = get_data()\n",
+ "data.head()\n",
+ "data.groupby(\"State\").count()\n",
+ "\n",
+ "y = data['State']\n",
+ "X = data.drop(['State','Launched','Deadline'], axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = pd.read_csv('data/kickstarter_projects.csv')\n",
+ "\n",
+ "\n",
+ "data = data.drop([\"ID\",\"Name\"],axis=1)\n",
+ "data = data[(data[\"State\"] == \"Successful\") | (data[\"State\"] == \"Failed\")]\n",
+ "data[\"Deadline\"] = pd.to_datetime(data[\"Deadline\"],format='%Y-%m-%d')\n",
+ "data[\"Launched\"] = pd.to_datetime(data[\"Launched\"],format='%Y-%m-%d %H:%M:%S')\n",
+ "data[\"Duration\"] = (data[\"Deadline\"] - data[\"Launched\"]).dt.days\n",
+ "\n",
+ "data, transform_data = transform_strings_to_numerical(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Model Coefficients: [[ 0.02520122 0.00417009 0.04143354 -0.10483769 0.10516741 0.08317194\n",
+ " 0.00119811]]\n",
+ "Model Intercept: [0.00554605]\n",
+ "Model Score: [0 0 0 ... 0 1 0]\n",
+ "Confusion Matrix: [[39351 56]\n",
+ " [ 0 26886]]\n",
+ "0.9989596492531768\n"
+ ]
+ }
+ ],
+ "source": [
+ "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state = 1337)\n",
+ "X_train.shape, X_test.shape, y_train.shape, y_test.shape\n",
+ "\n",
+ "model = LogisticRegression(max_iter=1000,penalty=\"l2\",C=0.1)\n",
+ "# fit the model to the training data\n",
+ "model.fit(X_train, y_train)\n",
+ "\n",
+ "# predict the target values for the test data\n",
+ "y_pred = model.predict(X_test)\n",
+ "\n",
+ "print(f\"Model Coefficients: {model.coef_}\")\n",
+ "print(f\"Model Intercept: {model.intercept_}\")\n",
+ "print(f\"Model Score: {y_pred}\")\n",
+ "print(f'Confusion Matrix: {confusion_matrix(y_test, y_pred)}')\n",
+ "\n",
+ "metric_value = f1_score(y_test, y_pred)\n",
+ "print(metric_value)"
]
}
],
diff --git a/requirements.txt b/requirements.txt
index f82b4b8..a2fcb07 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -9,4 +9,5 @@ jupyterlab-dash==0.1.0a3
scikit-learn==1.2.2
statsmodels==0.13.5
pytest==7.3.1
-import-ipynb
\ No newline at end of file
+xgboost==2.1.1
+import-ipynb
diff --git a/test.ipynb b/test.ipynb
index e69de29..6039a6c 100644
--- a/test.ipynb
+++ b/test.ipynb
@@ -0,0 +1,541 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from sklearn.preprocessing import LabelEncoder\n",
+ "from sklearn.metrics import precision_score, recall_score, f1_score, accuracy_score\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "data = pd.read_csv('data/kickstarter_projects.csv')\n",
+ "\n",
+ "data = data.drop([\"ID\",\"Name\"],axis=1)\n",
+ "data = data[(data[\"State\"] == \"Successful\") | (data[\"State\"] == \"Failed\")]\n",
+ "data[\"Deadline\"] = pd.to_datetime(data[\"Deadline\"],format='%Y-%m-%d')\n",
+ "data[\"Launched\"] = pd.to_datetime(data[\"Launched\"],format='%Y-%m-%d %H:%M:%S')\n",
+ "data[\"Duration\"] = (data[\"Deadline\"] - data[\"Launched\"]).dt.days\n",
+ "\n",
+ "for column in data.columns:\n",
+ " # If data type is an object, for example a string, we want to convert the column to numerical values\n",
+ " if data[column].dtype == 'object' and data[column].dtype != 'datetime64[ns]':\n",
+ " le = LabelEncoder()\n",
+ " data[column] = le.fit_transform(data[column])\n",
+ "\n",
+ "#data, transform_data = transform_strings_to_numerical(data)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "y = data['State']\n",
+ "X = data.drop(['State','Launched','Deadline'], axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "