diff --git a/.DS_Store b/.DS_Store new file mode 100644 index 0000000..f6c3eec Binary files /dev/null and b/.DS_Store differ diff --git a/your-code/.DS_Store b/your-code/.DS_Store new file mode 100644 index 0000000..5008ddf Binary files /dev/null and b/your-code/.DS_Store differ diff --git a/your-code/.ipynb_checkpoints/lab_imbalance-checkpoint.ipynb b/your-code/.ipynb_checkpoints/lab_imbalance-checkpoint.ipynb new file mode 100644 index 0000000..d02b422 --- /dev/null +++ b/your-code/.ipynb_checkpoints/lab_imbalance-checkpoint.ipynb @@ -0,0 +1,600 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Imbalanced Classes\n", + "## In this lab, we are going to explore a case of imbalanced classes. \n", + "\n", + "\n", + "Like we disussed in class, when we have noisy data, if we are not careful, we can end up fitting our model to the noise in the data and not the 'signal'-- the factors that actually determine the outcome. This is called overfitting, and results in good results in training, and in bad results when the model is applied to real data. Similarly, we could have a model that is too simplistic to accurately model the signal. This produces a model that doesnt work well (ever). \n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### First, download the data from: https://www.kaggle.com/datasets/chitwanmanchanda/fraudulent-transactions-data?resource=download . Import the dataset and provide some discriptive statistics and plots. What do you think will be the important features in determining the outcome?\n", + "### Note: don't use the entire dataset, use a sample instead, with n=100000 elements, so your computer doesn't freeze." + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "from sklearn.preprocessing import StandardScaler\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.linear_model import LogisticRegression\n", + "from sklearn.metrics import accuracy_score\n", + "from sklearn.ensemble import RandomForestClassifier\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import accuracy_score, classification_report\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Path to your downloaded CSV file\n", + "data_path = '/Users/gopikagowthaman/Desktop/IRONHACK/week19/lab-imbalance/your-code/Fraud.csv'\n", + "\n", + "# Read the first 100,000 rows\n", + "fraud = pd.read_csv(data_path, nrows=100000)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " step type amount nameOrig oldbalanceOrg newbalanceOrig \\\n", + "0 1 PAYMENT 9839.64 C1231006815 170136.0 160296.36 \n", + "1 1 PAYMENT 1864.28 C1666544295 21249.0 19384.72 \n", + "2 1 TRANSFER 181.00 C1305486145 181.0 0.00 \n", + "3 1 CASH_OUT 181.00 C840083671 181.0 0.00 \n", + "4 1 PAYMENT 11668.14 C2048537720 41554.0 29885.86 \n", + "\n", + " nameDest oldbalanceDest newbalanceDest isFraud isFlaggedFraud \n", + "0 M1979787155 0.0 0.0 0 0 \n", + "1 M2044282225 0.0 0.0 0 0 \n", + "2 C553264065 0.0 0.0 1 0 \n", + "3 C38997010 21182.0 0.0 1 0 \n", + "4 M1230701703 0.0 0.0 0 0 \n", + " step amount oldbalanceOrg newbalanceOrig \\\n", + "count 100000.000000 1.000000e+05 1.000000e+05 1.000000e+05 \n", + "mean 8.499640 1.736022e+05 8.777575e+05 8.940619e+05 \n", + "std 1.825545 3.443003e+05 2.673284e+06 2.711318e+06 \n", + "min 1.000000 3.200000e-01 0.000000e+00 0.000000e+00 \n", + "25% 8.000000 9.963562e+03 0.000000e+00 0.000000e+00 \n", + "50% 9.000000 5.274552e+04 2.006150e+04 0.000000e+00 \n", + "75% 10.000000 2.117631e+05 1.901920e+05 2.148132e+05 \n", + "max 10.000000 1.000000e+07 3.379739e+07 3.400874e+07 \n", + "\n", + " oldbalanceDest newbalanceDest isFraud isFlaggedFraud \n", + "count 1.000000e+05 1.000000e+05 100000.000000 100000.0 \n", + "mean 8.805048e+05 1.184041e+06 0.001160 0.0 \n", + "std 2.402267e+06 2.802350e+06 0.034039 0.0 \n", + "min 0.000000e+00 0.000000e+00 0.000000 0.0 \n", + "25% 0.000000e+00 0.000000e+00 0.000000 0.0 \n", + "50% 2.083943e+04 4.990918e+04 0.000000 0.0 \n", + "75% 5.882724e+05 1.058186e+06 0.000000 0.0 \n", + "max 3.400874e+07 3.894623e+07 1.000000 0.0 \n", + "\n", + "RangeIndex: 100000 entries, 0 to 99999\n", + "Data columns (total 11 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 step 100000 non-null int64 \n", + " 1 type 100000 non-null object \n", + " 2 amount 100000 non-null float64\n", + " 3 nameOrig 100000 non-null object \n", + " 4 oldbalanceOrg 100000 non-null float64\n", + " 5 newbalanceOrig 100000 non-null float64\n", + " 6 nameDest 100000 non-null object \n", + " 7 oldbalanceDest 100000 non-null float64\n", + " 8 newbalanceDest 100000 non-null float64\n", + " 9 isFraud 100000 non-null int64 \n", + " 10 isFlaggedFraud 100000 non-null int64 \n", + "dtypes: float64(5), int64(3), object(3)\n", + "memory usage: 8.4+ MB\n", + "None\n" + ] + } + ], + "source": [ + "# Display first few rows\n", + "print(fraud.head())\n", + "\n", + "# Summary statistics\n", + "print(fraud.describe())\n", + "\n", + "# Information about data types and missing values\n", + "print(fraud.info())\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Filter numeric columns only\n", + "numeric_fraud = fraud.select_dtypes(include=[float, int])\n", + "\n", + "# Calculate the correlation matrix\n", + "corr_matrix = numeric_fraud.corr()\n", + "\n", + "# Plot the correlation matrix\n", + "plt.figure(figsize=(12, 8))\n", + "sns.heatmap(corr_matrix, annot=True, fmt=\".2f\", cmap='coolwarm', vmin=-1, vmax=1)\n", + "plt.title(\"Correlation Matrix of Numeric Features\")\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "isFraud 1.000000\n", + "amount 0.036422\n", + "oldbalanceOrg -0.004144\n", + "newbalanceDest -0.006394\n", + "oldbalanceDest -0.009266\n", + "newbalanceOrig -0.010872\n", + "step -0.051329\n", + "isFlaggedFraud NaN\n", + "Name: isFraud, dtype: float64\n" + ] + } + ], + "source": [ + "# Ensure that we filter numeric columns from the DataFrame\n", + "numeric_fraud = fraud.select_dtypes(include=[float, int])\n", + "\n", + "# Calculate the correlation matrix\n", + "corr_matrix = numeric_fraud.corr()\n", + "\n", + "# Check if 'isFraud' exists and calculate correlations with it\n", + "if 'isFraud' in corr_matrix.columns:\n", + " # Sort correlations with 'isFraud' in descending order\n", + " correlations_with_target = corr_matrix['isFraud'].sort_values(ascending=False)\n", + " # Display the correlations\n", + " print(correlations_with_target)\n", + "else:\n", + " print(\"'isFraud' column not found in the dataset.\")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### What is the distribution of the outcome? " + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Not Fraudulent (0): 99884 transactions\n", + "Fraudulent (1): 116 transactions\n" + ] + } + ], + "source": [ + "# Your response here\n", + "# Count the number of occurrences for each class (0: Non-Fraud, 1: Fraud)\n", + "class_distribution = fraud['isFraud'].value_counts()\n", + "\n", + "# Display the results\n", + "print(f\"Not Fraudulent (0): {class_distribution[0]} transactions\")\n", + "print(f\"Fraudulent (1): {class_distribution[1]} transactions\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting the distribution of the 'isFraud' column to show the outcome distribution\n", + "\n", + "plt.figure(figsize=(6, 4))\n", + "sns.countplot(x='isFraud', data=fraud)\n", + "plt.title('Distribution of Fraudulent vs Non-Fraudulent Transactions')\n", + "plt.xlabel('Transaction Class (0: Non-Fraud, 1: Fraud)')\n", + "plt.ylabel('Count')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Clean the dataset. Pre-process it to make it suitable for ML training. Feel free to explore, drop, encode, transform, etc. Whatever you feel will improve the model score." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
stepamountoldbalanceOrgnewbalanceOrigoldbalanceDestnewbalanceDestisFraudisFlaggedFraudtype_CASH_OUTtype_DEBITtype_PAYMENTtype_TRANSFER
0-4.108186-0.475641-0.264702-0.270632-0.366533-0.42251900.0FalseFalseTrueFalse
1-4.108186-0.498805-0.320397-0.322604-0.366533-0.42251900.0FalseFalseTrueFalse
2-4.108186-0.503694-0.328278-0.329753-0.366533-0.42251910.0FalseFalseFalseTrue
3-4.108186-0.503694-0.328278-0.329753-0.357715-0.42251910.0TrueFalseFalseFalse
4-4.108186-0.470330-0.312802-0.318731-0.366533-0.42251900.0FalseFalseTrueFalse
\n", + "
" + ], + "text/plain": [ + " step amount oldbalanceOrg newbalanceOrig oldbalanceDest \\\n", + "0 -4.108186 -0.475641 -0.264702 -0.270632 -0.366533 \n", + "1 -4.108186 -0.498805 -0.320397 -0.322604 -0.366533 \n", + "2 -4.108186 -0.503694 -0.328278 -0.329753 -0.366533 \n", + "3 -4.108186 -0.503694 -0.328278 -0.329753 -0.357715 \n", + "4 -4.108186 -0.470330 -0.312802 -0.318731 -0.366533 \n", + "\n", + " newbalanceDest isFraud isFlaggedFraud type_CASH_OUT type_DEBIT \\\n", + "0 -0.422519 0 0.0 False False \n", + "1 -0.422519 0 0.0 False False \n", + "2 -0.422519 1 0.0 False False \n", + "3 -0.422519 1 0.0 True False \n", + "4 -0.422519 0 0.0 False False \n", + "\n", + " type_PAYMENT type_TRANSFER \n", + "0 True False \n", + "1 True False \n", + "2 False True \n", + "3 False False \n", + "4 True False " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Dropping irrelevant features\n", + "fraud = pd.read_csv('/Users/gopikagowthaman/Desktop/IRONHACK/week19/lab-imbalance/your-code/Fraud.csv', nrows=100000) # Reload dataset (assuming fraud dataset is available)\n", + "\n", + "# Dropping 'nameOrig' and 'nameDest' columns as they are not useful for predictions\n", + "fraud_cleaned = fraud.drop(['nameOrig', 'nameDest'], axis=1)\n", + "\n", + "# One-Hot Encoding the 'type' column\n", + "fraud_cleaned = pd.get_dummies(fraud_cleaned, columns=['type'], drop_first=True)\n", + "\n", + "# Standardizing numerical columns (excluding 'isFraud')\n", + "scaler = StandardScaler()\n", + "\n", + "# Select numerical columns, excluding 'isFraud'\n", + "numeric_columns = fraud_cleaned.select_dtypes(include=['float64', 'int64']).columns\n", + "numeric_columns = numeric_columns.drop('isFraud') # Drop 'isFraud' from the numeric columns\n", + "\n", + "# Apply StandardScaler to the remaining numerical columns\n", + "fraud_cleaned[numeric_columns] = scaler.fit_transform(fraud_cleaned[numeric_columns])\n", + "\n", + "\n", + "fraud_cleaned.head()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Run a logisitc regression classifier and evaluate its accuracy." + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy of Logistic Regression model: 0.9989\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 29967\n", + " 1 1.00 0.03 0.06 33\n", + "\n", + " accuracy 1.00 30000\n", + " macro avg 1.00 0.52 0.53 30000\n", + "weighted avg 1.00 1.00 1.00 30000\n", + "\n" + ] + } + ], + "source": [ + "# Assuming 'isFraud' is the target column\n", + "X = fraud_cleaned.drop('isFraud', axis=1)\n", + "y = fraud_cleaned['isFraud']\n", + "\n", + "# Split the dataset into training and test sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", + "\n", + "# Initialize and train the Logistic Regression model\n", + "log_reg = LogisticRegression(max_iter=1000) # max_iter set to 1000 to ensure convergence\n", + "log_reg.fit(X_train, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred = log_reg.predict(X_test)\n", + "\n", + "# Evaluate the accuracy of the model\n", + "accuracy = accuracy_score(y_test, y_pred)\n", + "print(f'Accuracy of Logistic Regression model: {accuracy:.4f}')\n", + "\n", + "# Print classification report for detailed evaluation\n", + "print(classification_report(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Now pick a model of your choice and evaluate its accuracy." + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy of Random Forest model: 0.9994\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 29967\n", + " 1 1.00 0.42 0.60 33\n", + "\n", + " accuracy 1.00 30000\n", + " macro avg 1.00 0.71 0.80 30000\n", + "weighted avg 1.00 1.00 1.00 30000\n", + "\n" + ] + } + ], + "source": [ + "# Assuming 'isFraud' is the target column\n", + "X = fraud_cleaned.drop('isFraud', axis=1)\n", + "y = fraud_cleaned['isFraud']\n", + "\n", + "# Split the dataset into training and test sets (70% train, 30% test)\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", + "\n", + "# Initialize the Random Forest Classifier\n", + "rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)\n", + "\n", + "# Train the model\n", + "rf_classifier.fit(X_train, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred = rf_classifier.predict(X_test)\n", + "\n", + "# Evaluate the accuracy of the model\n", + "accuracy = accuracy_score(y_test, y_pred)\n", + "print(f'Accuracy of Random Forest model: {accuracy:.4f}')\n", + "\n", + "# Print classification report for detailed evaluation\n", + "print(classification_report(y_test, y_pred))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Which model worked better and how do you know?" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Your response here\n", + "\"\"\"\n", + "Random Forest is the better model overall because it significantly outperforms Logistic Regression in terms of recall and F1-score for the minority class (fraud cases). \n", + "This is critical in fraud detection, where missing a fraudulent case can have serious consequences.Random Forest: 0.42 for fraud (class 1)\n", + "\n", + "Logistic Regression: 0.03 for fraud (class 1)\n", + "Recall is a critical metric in this case because it measures how many of the actual fraud cases (class 1) were correctly identified by the models. \n", + "The Random Forest is able to catch 42% of fraud cases, while Logistic Regression only captures 3%, which means Random Forest is much better at identifying fraudulent cases.\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." + ] + } + ], + "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": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/your-code/lab_imbalance.ipynb b/your-code/lab_imbalance.ipynb index dbb15e1..d02b422 100644 --- a/your-code/lab_imbalance.ipynb +++ b/your-code/lab_imbalance.ipynb @@ -1,147 +1,600 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Inbalanced Classes\n", - "## In this lab, we are going to explore a case of imbalanced classes. \n", - "\n", - "\n", - "Like we disussed in class, when we have noisy data, if we are not careful, we can end up fitting our model to the noise in the data and not the 'signal'-- the factors that actually determine the outcome. This is called overfitting, and results in good results in training, and in bad results when the model is applied to real data. Similarly, we could have a model that is too simplistic to accurately model the signal. This produces a model that doesnt work well (ever). \n" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### First, download the data from: https://www.kaggle.com/datasets/chitwanmanchanda/fraudulent-transactions-data?resource=download . Import the dataset and provide some discriptive statistics and plots. What do you think will be the important features in determining the outcome?\n", - "### Note: don't use the entire dataset, use a sample instead, with n=100000 elements, so your computer doesn't freeze." - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### What is the distribution of the outcome? " - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your response here" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Clean the dataset. Pre-process it to make it suitable for ML training. Feel free to explore, drop, encode, transform, etc. Whatever you feel will improve the model score." - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here\n" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Run a logisitc regression classifier and evaluate its accuracy." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Now pick a model of your choice and evaluate its accuracy." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# Your code here" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Which model worked better and how do you know?" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [], - "source": [ - "# Your response here" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." - ] - } - ], - "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": "3.6.8" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Imbalanced Classes\n", + "## In this lab, we are going to explore a case of imbalanced classes. \n", + "\n", + "\n", + "Like we disussed in class, when we have noisy data, if we are not careful, we can end up fitting our model to the noise in the data and not the 'signal'-- the factors that actually determine the outcome. This is called overfitting, and results in good results in training, and in bad results when the model is applied to real data. Similarly, we could have a model that is too simplistic to accurately model the signal. This produces a model that doesnt work well (ever). \n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### First, download the data from: https://www.kaggle.com/datasets/chitwanmanchanda/fraudulent-transactions-data?resource=download . Import the dataset and provide some discriptive statistics and plots. What do you think will be the important features in determining the outcome?\n", + "### Note: don't use the entire dataset, use a sample instead, with n=100000 elements, so your computer doesn't freeze." + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "# Your code here\n", + "import pandas as pd\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import seaborn as sns\n", + "from sklearn.preprocessing import StandardScaler\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.linear_model import LogisticRegression\n", + "from sklearn.metrics import accuracy_score\n", + "from sklearn.ensemble import RandomForestClassifier\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import accuracy_score, classification_report\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Path to your downloaded CSV file\n", + "data_path = '/Users/gopikagowthaman/Desktop/IRONHACK/week19/lab-imbalance/your-code/Fraud.csv'\n", + "\n", + "# Read the first 100,000 rows\n", + "fraud = pd.read_csv(data_path, nrows=100000)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " step type amount nameOrig oldbalanceOrg newbalanceOrig \\\n", + "0 1 PAYMENT 9839.64 C1231006815 170136.0 160296.36 \n", + "1 1 PAYMENT 1864.28 C1666544295 21249.0 19384.72 \n", + "2 1 TRANSFER 181.00 C1305486145 181.0 0.00 \n", + "3 1 CASH_OUT 181.00 C840083671 181.0 0.00 \n", + "4 1 PAYMENT 11668.14 C2048537720 41554.0 29885.86 \n", + "\n", + " nameDest oldbalanceDest newbalanceDest isFraud isFlaggedFraud \n", + "0 M1979787155 0.0 0.0 0 0 \n", + "1 M2044282225 0.0 0.0 0 0 \n", + "2 C553264065 0.0 0.0 1 0 \n", + "3 C38997010 21182.0 0.0 1 0 \n", + "4 M1230701703 0.0 0.0 0 0 \n", + " step amount oldbalanceOrg newbalanceOrig \\\n", + "count 100000.000000 1.000000e+05 1.000000e+05 1.000000e+05 \n", + "mean 8.499640 1.736022e+05 8.777575e+05 8.940619e+05 \n", + "std 1.825545 3.443003e+05 2.673284e+06 2.711318e+06 \n", + "min 1.000000 3.200000e-01 0.000000e+00 0.000000e+00 \n", + "25% 8.000000 9.963562e+03 0.000000e+00 0.000000e+00 \n", + "50% 9.000000 5.274552e+04 2.006150e+04 0.000000e+00 \n", + "75% 10.000000 2.117631e+05 1.901920e+05 2.148132e+05 \n", + "max 10.000000 1.000000e+07 3.379739e+07 3.400874e+07 \n", + "\n", + " oldbalanceDest newbalanceDest isFraud isFlaggedFraud \n", + "count 1.000000e+05 1.000000e+05 100000.000000 100000.0 \n", + "mean 8.805048e+05 1.184041e+06 0.001160 0.0 \n", + "std 2.402267e+06 2.802350e+06 0.034039 0.0 \n", + "min 0.000000e+00 0.000000e+00 0.000000 0.0 \n", + "25% 0.000000e+00 0.000000e+00 0.000000 0.0 \n", + "50% 2.083943e+04 4.990918e+04 0.000000 0.0 \n", + "75% 5.882724e+05 1.058186e+06 0.000000 0.0 \n", + "max 3.400874e+07 3.894623e+07 1.000000 0.0 \n", + "\n", + "RangeIndex: 100000 entries, 0 to 99999\n", + "Data columns (total 11 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 step 100000 non-null int64 \n", + " 1 type 100000 non-null object \n", + " 2 amount 100000 non-null float64\n", + " 3 nameOrig 100000 non-null object \n", + " 4 oldbalanceOrg 100000 non-null float64\n", + " 5 newbalanceOrig 100000 non-null float64\n", + " 6 nameDest 100000 non-null object \n", + " 7 oldbalanceDest 100000 non-null float64\n", + " 8 newbalanceDest 100000 non-null float64\n", + " 9 isFraud 100000 non-null int64 \n", + " 10 isFlaggedFraud 100000 non-null int64 \n", + "dtypes: float64(5), int64(3), object(3)\n", + "memory usage: 8.4+ MB\n", + "None\n" + ] + } + ], + "source": [ + "# Display first few rows\n", + "print(fraud.head())\n", + "\n", + "# Summary statistics\n", + "print(fraud.describe())\n", + "\n", + "# Information about data types and missing values\n", + "print(fraud.info())\n" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Filter numeric columns only\n", + "numeric_fraud = fraud.select_dtypes(include=[float, int])\n", + "\n", + "# Calculate the correlation matrix\n", + "corr_matrix = numeric_fraud.corr()\n", + "\n", + "# Plot the correlation matrix\n", + "plt.figure(figsize=(12, 8))\n", + "sns.heatmap(corr_matrix, annot=True, fmt=\".2f\", cmap='coolwarm', vmin=-1, vmax=1)\n", + "plt.title(\"Correlation Matrix of Numeric Features\")\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "isFraud 1.000000\n", + "amount 0.036422\n", + "oldbalanceOrg -0.004144\n", + "newbalanceDest -0.006394\n", + "oldbalanceDest -0.009266\n", + "newbalanceOrig -0.010872\n", + "step -0.051329\n", + "isFlaggedFraud NaN\n", + "Name: isFraud, dtype: float64\n" + ] + } + ], + "source": [ + "# Ensure that we filter numeric columns from the DataFrame\n", + "numeric_fraud = fraud.select_dtypes(include=[float, int])\n", + "\n", + "# Calculate the correlation matrix\n", + "corr_matrix = numeric_fraud.corr()\n", + "\n", + "# Check if 'isFraud' exists and calculate correlations with it\n", + "if 'isFraud' in corr_matrix.columns:\n", + " # Sort correlations with 'isFraud' in descending order\n", + " correlations_with_target = corr_matrix['isFraud'].sort_values(ascending=False)\n", + " # Display the correlations\n", + " print(correlations_with_target)\n", + "else:\n", + " print(\"'isFraud' column not found in the dataset.\")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### What is the distribution of the outcome? " + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Not Fraudulent (0): 99884 transactions\n", + "Fraudulent (1): 116 transactions\n" + ] + } + ], + "source": [ + "# Your response here\n", + "# Count the number of occurrences for each class (0: Non-Fraud, 1: Fraud)\n", + "class_distribution = fraud['isFraud'].value_counts()\n", + "\n", + "# Display the results\n", + "print(f\"Not Fraudulent (0): {class_distribution[0]} transactions\")\n", + "print(f\"Fraudulent (1): {class_distribution[1]} transactions\")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting the distribution of the 'isFraud' column to show the outcome distribution\n", + "\n", + "plt.figure(figsize=(6, 4))\n", + "sns.countplot(x='isFraud', data=fraud)\n", + "plt.title('Distribution of Fraudulent vs Non-Fraudulent Transactions')\n", + "plt.xlabel('Transaction Class (0: Non-Fraud, 1: Fraud)')\n", + "plt.ylabel('Count')\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Clean the dataset. Pre-process it to make it suitable for ML training. Feel free to explore, drop, encode, transform, etc. Whatever you feel will improve the model score." + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
stepamountoldbalanceOrgnewbalanceOrigoldbalanceDestnewbalanceDestisFraudisFlaggedFraudtype_CASH_OUTtype_DEBITtype_PAYMENTtype_TRANSFER
0-4.108186-0.475641-0.264702-0.270632-0.366533-0.42251900.0FalseFalseTrueFalse
1-4.108186-0.498805-0.320397-0.322604-0.366533-0.42251900.0FalseFalseTrueFalse
2-4.108186-0.503694-0.328278-0.329753-0.366533-0.42251910.0FalseFalseFalseTrue
3-4.108186-0.503694-0.328278-0.329753-0.357715-0.42251910.0TrueFalseFalseFalse
4-4.108186-0.470330-0.312802-0.318731-0.366533-0.42251900.0FalseFalseTrueFalse
\n", + "
" + ], + "text/plain": [ + " step amount oldbalanceOrg newbalanceOrig oldbalanceDest \\\n", + "0 -4.108186 -0.475641 -0.264702 -0.270632 -0.366533 \n", + "1 -4.108186 -0.498805 -0.320397 -0.322604 -0.366533 \n", + "2 -4.108186 -0.503694 -0.328278 -0.329753 -0.366533 \n", + "3 -4.108186 -0.503694 -0.328278 -0.329753 -0.357715 \n", + "4 -4.108186 -0.470330 -0.312802 -0.318731 -0.366533 \n", + "\n", + " newbalanceDest isFraud isFlaggedFraud type_CASH_OUT type_DEBIT \\\n", + "0 -0.422519 0 0.0 False False \n", + "1 -0.422519 0 0.0 False False \n", + "2 -0.422519 1 0.0 False False \n", + "3 -0.422519 1 0.0 True False \n", + "4 -0.422519 0 0.0 False False \n", + "\n", + " type_PAYMENT type_TRANSFER \n", + "0 True False \n", + "1 True False \n", + "2 False True \n", + "3 False False \n", + "4 True False " + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Dropping irrelevant features\n", + "fraud = pd.read_csv('/Users/gopikagowthaman/Desktop/IRONHACK/week19/lab-imbalance/your-code/Fraud.csv', nrows=100000) # Reload dataset (assuming fraud dataset is available)\n", + "\n", + "# Dropping 'nameOrig' and 'nameDest' columns as they are not useful for predictions\n", + "fraud_cleaned = fraud.drop(['nameOrig', 'nameDest'], axis=1)\n", + "\n", + "# One-Hot Encoding the 'type' column\n", + "fraud_cleaned = pd.get_dummies(fraud_cleaned, columns=['type'], drop_first=True)\n", + "\n", + "# Standardizing numerical columns (excluding 'isFraud')\n", + "scaler = StandardScaler()\n", + "\n", + "# Select numerical columns, excluding 'isFraud'\n", + "numeric_columns = fraud_cleaned.select_dtypes(include=['float64', 'int64']).columns\n", + "numeric_columns = numeric_columns.drop('isFraud') # Drop 'isFraud' from the numeric columns\n", + "\n", + "# Apply StandardScaler to the remaining numerical columns\n", + "fraud_cleaned[numeric_columns] = scaler.fit_transform(fraud_cleaned[numeric_columns])\n", + "\n", + "\n", + "fraud_cleaned.head()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Run a logisitc regression classifier and evaluate its accuracy." + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy of Logistic Regression model: 0.9989\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 29967\n", + " 1 1.00 0.03 0.06 33\n", + "\n", + " accuracy 1.00 30000\n", + " macro avg 1.00 0.52 0.53 30000\n", + "weighted avg 1.00 1.00 1.00 30000\n", + "\n" + ] + } + ], + "source": [ + "# Assuming 'isFraud' is the target column\n", + "X = fraud_cleaned.drop('isFraud', axis=1)\n", + "y = fraud_cleaned['isFraud']\n", + "\n", + "# Split the dataset into training and test sets\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", + "\n", + "# Initialize and train the Logistic Regression model\n", + "log_reg = LogisticRegression(max_iter=1000) # max_iter set to 1000 to ensure convergence\n", + "log_reg.fit(X_train, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred = log_reg.predict(X_test)\n", + "\n", + "# Evaluate the accuracy of the model\n", + "accuracy = accuracy_score(y_test, y_pred)\n", + "print(f'Accuracy of Logistic Regression model: {accuracy:.4f}')\n", + "\n", + "# Print classification report for detailed evaluation\n", + "print(classification_report(y_test, y_pred))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Now pick a model of your choice and evaluate its accuracy." + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy of Random Forest model: 0.9994\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 29967\n", + " 1 1.00 0.42 0.60 33\n", + "\n", + " accuracy 1.00 30000\n", + " macro avg 1.00 0.71 0.80 30000\n", + "weighted avg 1.00 1.00 1.00 30000\n", + "\n" + ] + } + ], + "source": [ + "# Assuming 'isFraud' is the target column\n", + "X = fraud_cleaned.drop('isFraud', axis=1)\n", + "y = fraud_cleaned['isFraud']\n", + "\n", + "# Split the dataset into training and test sets (70% train, 30% test)\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n", + "\n", + "# Initialize the Random Forest Classifier\n", + "rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)\n", + "\n", + "# Train the model\n", + "rf_classifier.fit(X_train, y_train)\n", + "\n", + "# Make predictions on the test set\n", + "y_pred = rf_classifier.predict(X_test)\n", + "\n", + "# Evaluate the accuracy of the model\n", + "accuracy = accuracy_score(y_test, y_pred)\n", + "print(f'Accuracy of Random Forest model: {accuracy:.4f}')\n", + "\n", + "# Print classification report for detailed evaluation\n", + "print(classification_report(y_test, y_pred))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Which model worked better and how do you know?" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Your response here\n", + "\"\"\"\n", + "Random Forest is the better model overall because it significantly outperforms Logistic Regression in terms of recall and F1-score for the minority class (fraud cases). \n", + "This is critical in fraud detection, where missing a fraudulent case can have serious consequences.Random Forest: 0.42 for fraud (class 1)\n", + "\n", + "Logistic Regression: 0.03 for fraud (class 1)\n", + "Recall is a critical metric in this case because it measures how many of the actual fraud cases (class 1) were correctly identified by the models. \n", + "The Random Forest is able to catch 42% of fraud cases, while Logistic Regression only captures 3%, which means Random Forest is much better at identifying fraudulent cases.\n", + "\"\"\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Note: before doing the first commit, make sure you don't include the large csv file, either by adding it to .gitignore, or by deleting it." + ] + } + ], + "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": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}