From 42ba07d51d178ef0a544d8e5bf3d71b50310ba80 Mon Sep 17 00:00:00 2001 From: akorade Date: Tue, 2 Dec 2025 18:48:22 -0500 Subject: [PATCH 1/2] Implement file reading and patient summary in assignment 2 Added code to read and print data from the first inflammation file with error handling for missing files. Implemented the patient_summary function to compute mean, max, and min using numpy, and updated detect_problems to warn if any patient has a mean inflammation of 0. Updated notebook metadata to reflect the current Python environment. --- 02_activities/assignments/assignment_2.ipynb | 193 +++++++++++++++++-- 1 file changed, 181 insertions(+), 12 deletions(-) diff --git a/02_activities/assignments/assignment_2.ipynb b/02_activities/assignments/assignment_2.ipynb index fdaead283..a12b2550e 100644 --- a/02_activities/assignments/assignment_2.ipynb +++ b/02_activities/assignments/assignment_2.ipynb @@ -72,11 +72,140 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": { "id": "n0m48JsS-nMC" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Data from the first inflammation file:\n", + "--------------------------------\n", + "0,0,1,3,1,2,4,7,8,3,3,3,10,5,7,4,7,7,12,18,6,13,11,11,7,7,4,6,8,8,4,4,5,7,3,4,2,3,0,0\n", + "\n", + "0,1,2,1,2,1,3,2,2,6,10,11,5,9,4,4,7,16,8,6,18,4,12,5,12,7,11,5,11,3,3,5,4,4,5,5,1,1,0,1\n", + "\n", + "0,1,1,3,3,2,6,2,5,9,5,7,4,5,4,15,5,11,9,10,19,14,12,17,7,12,11,7,4,2,10,5,4,2,2,3,2,2,1,1\n", + "\n", + "0,0,2,0,4,2,2,1,6,7,10,7,9,13,8,8,15,10,10,7,17,4,4,7,6,15,6,4,9,11,3,5,6,3,3,4,2,3,2,1\n", + "\n", + "0,1,1,3,3,1,3,5,2,4,4,7,6,5,3,10,8,10,6,17,9,14,9,7,13,9,12,6,7,7,9,6,3,2,2,4,2,0,1,1\n", + "\n", + "0,0,1,2,2,4,2,1,6,4,7,6,6,9,9,15,4,16,18,12,12,5,18,9,5,3,10,3,12,7,8,4,7,3,5,4,4,3,2,1\n", + "\n", + "0,0,2,2,4,2,2,5,5,8,6,5,11,9,4,13,5,12,10,6,9,17,15,8,9,3,13,7,8,2,8,8,4,2,3,5,4,1,1,1\n", + "\n", + "0,0,1,2,3,1,2,3,5,3,7,8,8,5,10,9,15,11,18,19,20,8,5,13,15,10,6,10,6,7,4,9,3,5,2,5,3,2,2,1\n", + "\n", + "0,0,0,3,1,5,6,5,5,8,2,4,11,12,10,11,9,10,17,11,6,16,12,6,8,14,6,13,10,11,4,6,4,7,6,3,2,1,0,0\n", + "\n", + "0,1,1,2,1,3,5,3,5,8,6,8,12,5,13,6,13,8,16,8,18,15,16,14,12,7,3,8,9,11,2,5,4,5,1,4,1,2,0,0\n", + "\n", + "0,1,0,0,4,3,3,5,5,4,5,8,7,10,13,3,7,13,15,18,8,15,15,16,11,14,12,4,10,10,4,3,4,5,5,3,3,2,2,1\n", + "\n", + "0,1,0,0,3,4,2,7,8,5,2,8,11,5,5,8,14,11,6,11,9,16,18,6,12,5,4,3,5,7,8,3,5,4,5,5,4,0,1,1\n", + "\n", + "0,0,2,1,4,3,6,4,6,7,9,9,3,11,6,12,4,17,13,15,13,12,8,7,4,7,12,9,5,6,5,4,7,3,5,4,2,3,0,1\n", + "\n", + "0,0,0,0,1,3,1,6,6,5,5,6,3,6,13,3,10,13,9,16,15,9,11,4,6,4,11,11,12,3,5,8,7,4,6,4,1,3,0,0\n", + "\n", + "0,1,2,1,1,1,4,1,5,2,3,3,10,7,13,5,7,17,6,9,12,13,10,4,12,4,6,7,6,10,8,2,5,1,3,4,2,0,2,0\n", + "\n", + "0,1,1,0,1,2,4,3,6,4,7,5,5,7,5,10,7,8,18,17,9,8,12,11,11,11,14,6,11,2,10,9,5,6,5,3,4,2,2,0\n", + "\n", + "0,0,0,0,2,3,6,5,7,4,3,2,10,7,9,11,12,5,12,9,13,19,14,17,5,13,8,11,5,10,9,8,7,5,3,1,4,0,2,1\n", + "\n", + "0,0,0,1,2,1,4,3,6,7,4,2,12,6,12,4,14,7,8,14,13,19,6,9,12,6,4,13,6,7,2,3,6,5,4,2,3,0,1,0\n", + "\n", + "0,0,2,1,2,5,4,2,7,8,4,7,11,9,8,11,15,17,11,12,7,12,7,6,7,4,13,5,7,6,6,9,2,1,1,2,2,0,1,0\n", + "\n", + "0,1,2,0,1,4,3,2,2,7,3,3,12,13,11,13,6,5,9,16,9,19,16,11,8,9,14,12,11,9,6,6,6,1,1,2,4,3,1,1\n", + "\n", + "0,1,1,3,1,4,4,1,8,2,2,3,12,12,10,15,13,6,5,5,18,19,9,6,11,12,7,6,3,6,3,2,4,3,1,5,4,2,2,0\n", + "\n", + "0,0,2,3,2,3,2,6,3,8,7,4,6,6,9,5,12,12,8,5,12,10,16,7,14,12,5,4,6,9,8,5,6,6,1,4,3,0,2,0\n", + "\n", + "0,0,0,3,4,5,1,7,7,8,2,5,12,4,10,14,5,5,17,13,16,15,13,6,12,9,10,3,3,7,4,4,8,2,6,5,1,0,1,0\n", + "\n", + "0,1,1,1,1,3,3,2,6,3,9,7,8,8,4,13,7,14,11,15,14,13,5,13,7,14,9,10,5,11,5,3,5,1,1,4,4,1,2,0\n", + "\n", + "0,1,1,1,2,3,5,3,6,3,7,10,3,8,12,4,12,9,15,5,17,16,5,10,10,15,7,5,3,11,5,5,6,1,1,1,1,0,2,1\n", + "\n", + "0,0,2,1,3,3,2,7,4,4,3,8,12,9,12,9,5,16,8,17,7,11,14,7,13,11,7,12,12,7,8,5,7,2,2,4,1,1,1,0\n", + "\n", + "0,0,1,2,4,2,2,3,5,7,10,5,5,12,3,13,4,13,7,15,9,12,18,14,16,12,3,11,3,2,7,4,8,2,2,1,3,0,1,1\n", + "\n", + "0,0,1,1,1,5,1,5,2,2,4,10,4,8,14,6,15,6,12,15,15,13,7,17,4,5,11,4,8,7,9,4,5,3,2,5,4,3,2,1\n", + "\n", + "0,0,2,2,3,4,6,3,7,6,4,5,8,4,7,7,6,11,12,19,20,18,9,5,4,7,14,8,4,3,7,7,8,3,5,4,1,3,1,0\n", + "\n", + "0,0,0,1,4,4,6,3,8,6,4,10,12,3,3,6,8,7,17,16,14,15,17,4,14,13,4,4,12,11,6,9,5,5,2,5,2,1,0,1\n", + "\n", + "0,1,1,0,3,2,4,6,8,6,2,3,11,3,14,14,12,8,8,16,13,7,6,9,15,7,6,4,10,8,10,4,2,6,5,5,2,3,2,1\n", + "\n", + "0,0,2,3,3,4,5,3,6,7,10,5,10,13,14,3,8,10,9,9,19,15,15,6,8,8,11,5,5,7,3,6,6,4,5,2,2,3,0,0\n", + "\n", + "0,1,2,2,2,3,6,6,6,7,6,3,11,12,13,15,15,10,14,11,11,8,6,12,10,5,12,7,7,11,5,8,5,2,5,5,2,0,2,1\n", + "\n", + "0,0,2,1,3,5,6,7,5,8,9,3,12,10,12,4,12,9,13,10,10,6,10,11,4,15,13,7,3,4,2,9,7,2,4,2,1,2,1,1\n", + "\n", + "0,0,1,2,4,1,5,5,2,3,4,8,8,12,5,15,9,17,7,19,14,18,12,17,14,4,13,13,8,11,5,6,6,2,3,5,2,1,1,1\n", + "\n", + "0,0,0,3,1,3,6,4,3,4,8,3,4,8,3,11,5,7,10,5,15,9,16,17,16,3,8,9,8,3,3,9,5,1,6,5,4,2,2,0\n", + "\n", + "0,1,2,2,2,5,5,1,4,6,3,6,5,9,6,7,4,7,16,7,16,13,9,16,12,6,7,9,10,3,6,4,5,4,6,3,4,3,2,1\n", + "\n", + "0,1,1,2,3,1,5,1,2,2,5,7,6,6,5,10,6,7,17,13,15,16,17,14,4,4,10,10,10,11,9,9,5,4,4,2,1,0,1,0\n", + "\n", + "0,1,0,3,2,4,1,1,5,9,10,7,12,10,9,15,12,13,13,6,19,9,10,6,13,5,13,6,7,2,5,5,2,1,1,1,1,3,0,1\n", + "\n", + "0,1,1,3,1,1,5,5,3,7,2,2,3,12,4,6,8,15,16,16,15,4,14,5,13,10,7,10,6,3,2,3,6,3,3,5,4,3,2,1\n", + "\n", + "0,0,0,2,2,1,3,4,5,5,6,5,5,12,13,5,7,5,11,15,18,7,9,10,14,12,11,9,10,3,2,9,6,2,2,5,3,0,0,1\n", + "\n", + "0,0,1,3,3,1,2,1,8,9,2,8,10,3,8,6,10,13,11,17,19,6,4,11,6,12,7,5,5,4,4,8,2,6,6,4,2,2,0,0\n", + "\n", + "0,1,1,3,4,5,2,1,3,7,9,6,10,5,8,15,11,12,15,6,12,16,6,4,14,3,12,9,6,11,5,8,5,5,6,1,2,1,2,0\n", + "\n", + "0,0,1,3,1,4,3,6,7,8,5,7,11,3,6,11,6,10,6,19,18,14,6,10,7,9,8,5,8,3,10,2,5,1,5,4,2,1,0,1\n", + "\n", + "0,1,1,3,3,4,4,6,3,4,9,9,7,6,8,15,12,15,6,11,6,18,5,14,15,12,9,8,3,6,10,6,8,7,2,5,4,3,1,1\n", + "\n", + "0,1,2,2,4,3,1,4,8,9,5,10,10,3,4,6,7,11,16,6,14,9,11,10,10,7,10,8,8,4,5,8,4,4,5,2,4,1,1,0\n", + "\n", + "0,0,2,3,4,5,4,6,2,9,7,4,9,10,8,11,16,12,15,17,19,10,18,13,15,11,8,4,7,11,6,7,6,5,1,3,1,0,0,0\n", + "\n", + "0,1,1,3,1,4,6,2,8,2,10,3,11,9,13,15,5,15,6,10,10,5,14,15,12,7,4,5,11,4,6,9,5,6,1,1,2,1,2,1\n", + "\n", + "0,0,1,3,2,5,1,2,7,6,6,3,12,9,4,14,4,6,12,9,12,7,11,7,16,8,13,6,7,6,10,7,6,3,1,5,4,3,0,0\n", + "\n", + "0,0,1,2,3,4,5,7,5,4,10,5,12,12,5,4,7,9,18,16,16,10,15,15,10,4,3,7,5,9,4,6,2,4,1,4,2,2,2,1\n", + "\n", + "0,1,2,1,1,3,5,3,6,3,10,10,11,10,13,10,13,6,6,14,5,4,5,5,9,4,12,7,7,4,7,9,3,3,6,3,4,1,2,0\n", + "\n", + "0,1,2,2,3,5,2,4,5,6,8,3,5,4,3,15,15,12,16,7,20,15,12,8,9,6,12,5,8,3,8,5,4,1,3,2,1,3,1,0\n", + "\n", + "0,0,0,2,4,4,5,3,3,3,10,4,4,4,14,11,15,13,10,14,11,17,9,11,11,7,10,12,10,10,10,8,7,5,2,2,4,1,2,1\n", + "\n", + "0,0,2,1,1,4,4,7,2,9,4,10,12,7,6,6,11,12,9,15,15,6,6,13,5,12,9,6,4,7,7,6,5,4,1,4,2,2,2,1\n", + "\n", + "0,1,2,1,1,4,5,4,4,5,9,7,10,3,13,13,8,9,17,16,16,15,12,13,5,12,10,9,11,9,4,5,5,2,2,5,1,0,0,1\n", + "\n", + "0,0,1,3,2,3,6,4,5,7,2,4,11,11,3,8,8,16,5,13,16,5,8,8,6,9,10,10,9,3,3,5,3,5,4,5,3,3,0,1\n", + "\n", + "0,1,1,2,2,5,1,7,4,2,5,5,4,6,6,4,16,11,14,16,14,14,8,17,4,14,13,7,6,3,7,7,5,6,3,4,2,2,1,1\n", + "\n", + "0,1,1,1,4,1,6,4,6,3,6,5,6,4,14,13,13,9,12,19,9,10,15,10,9,10,10,7,5,6,8,6,6,4,3,5,2,1,1,1\n", + "\n", + "0,0,0,1,4,5,6,3,8,7,9,10,8,6,5,12,15,5,10,5,8,13,18,17,14,9,13,4,10,11,10,8,8,6,5,5,2,0,2,0\n", + "\n", + "0,0,1,0,3,2,5,4,8,2,9,3,3,10,12,9,14,11,13,8,6,18,11,9,13,11,8,5,5,2,8,5,3,5,4,1,3,1,1,0\n", + "\n" + ] + } + ], "source": [ "all_paths = [\n", " \"../../05_src/data/assignment_2_data/inflammation_01.csv\",\n", @@ -92,11 +221,17 @@ " \"../../05_src/data/assignment_2_data/inflammation_11.csv\",\n", " \"../../05_src/data/assignment_2_data/inflammation_12.csv\"\n", "]\n", - "\n", - "with open(all_paths[0], 'r') as f:\n", + "try:\n", + " with open(all_paths[0], 'r') as f:\n", " # YOUR CODE HERE: Use the readline() or readlines() method to read the .csv file into a variable\n", - " \n", - " # YOUR CODE HERE: Iterate through the variable using a for loop and print each row for inspection" + " data = f.readlines()\n", + " # YOUR CODE HERE: Iterate through the variable using a for loop and print each row for inspection\n", + " print(\"Data from the first inflammation file:\")\n", + " print(\"--------------------------------\")\n", + " for row in data:\n", + " print(row)\n", + "except FileNotFoundError:\n", + " print(f\"Error: The file at path {all_paths[0]} was not found.\")\n" ] }, { @@ -130,12 +265,30 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "id": "82-bk4CBB1w4" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Collecting numpy\n", + " Downloading numpy-2.3.5-cp312-cp312-win_amd64.whl.metadata (60 kB)\n", + "Downloading numpy-2.3.5-cp312-cp312-win_amd64.whl (12.8 MB)\n", + " ---------------------------------------- 0.0/12.8 MB ? eta -:--:--\n", + " ---------- ----------------------------- 3.4/12.8 MB 25.2 MB/s eta 0:00:01\n", + " ------------------------------- -------- 10.0/12.8 MB 28.2 MB/s eta 0:00:01\n", + " ---------------------------------------- 12.8/12.8 MB 25.0 MB/s 0:00:00\n", + "Installing collected packages: numpy\n", + "Successfully installed numpy-2.3.5\n", + "Note: you may need to restart the kernel to use updated packages.\n" + ] + } + ], "source": [ + "%pip install numpy\n", "import numpy as np\n", "\n", "def patient_summary(file_path, operation):\n", @@ -145,12 +298,15 @@ " # Implement the specific operation based on the 'operation' argument\n", " if operation == 'mean':\n", " # YOUR CODE HERE: Calculate the mean (average) number of flare-ups for each patient\n", + " summary_values = np.mean(data, axis=ax)\n", "\n", " elif operation == 'max':\n", " # YOUR CODE HERE: Calculate the maximum number of flare-ups experienced by each patient\n", + " summary_values = np.max(data, axis=ax)\n", "\n", " elif operation == 'min':\n", " # YOUR CODE HERE: Calculate the minimum number of flare-ups experienced by each patient\n", + " summary_values = np.min(data, axis=ax)\n", "\n", " else:\n", " # If the operation is not one of the expected values, raise an error\n", @@ -161,11 +317,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "id": "3TYo0-1SDLrd" }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "60\n" + ] + } + ], "source": [ "# Test it out on the data file we read in and make sure the size is what we expect i.e., 60\n", "# Your output for the first file should be 60\n", @@ -261,6 +425,10 @@ "\n", "def detect_problems(file_path):\n", " #YOUR CODE HERE: Use patient_summary() to get the means and check_zeros() to check for zeros in the means\n", + " means = patient_summary(file_path, 'mean')\n", + " has_zeros = check_zeros(means)\n", + " if has_zeros:\n", + " print(\"Warning: At least one patient has a mean inflammation of 0.\")\n", "\n", " return" ] @@ -314,7 +482,8 @@ "provenance": [] }, "kernelspec": { - "display_name": "Python 3", + "display_name": ".venv", + "language": "python", "name": "python3" }, "language_info": { @@ -327,7 +496,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.8" + "version": "3.12.10" } }, "nbformat": 4, From c5ac476693da52251aa2993ed51e1d2dabd5294a Mon Sep 17 00:00:00 2001 From: akorade Date: Thu, 11 Dec 2025 10:29:42 -0500 Subject: [PATCH 2/2] Test negative scenarios Enhanced the test code to check min, max, and mean array lengths for patient data. Updated the detect_problems test to execute for all the input files --- 02_activities/assignments/assignment_2.ipynb | 74 ++++++++++++++------ 1 file changed, 53 insertions(+), 21 deletions(-) diff --git a/02_activities/assignments/assignment_2.ipynb b/02_activities/assignments/assignment_2.ipynb index a12b2550e..961b1c239 100644 --- a/02_activities/assignments/assignment_2.ipynb +++ b/02_activities/assignments/assignment_2.ipynb @@ -72,7 +72,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 4, "metadata": { "id": "n0m48JsS-nMC" }, @@ -265,7 +265,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": { "id": "82-bk4CBB1w4" }, @@ -274,15 +274,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Collecting numpy\n", - " Downloading numpy-2.3.5-cp312-cp312-win_amd64.whl.metadata (60 kB)\n", - "Downloading numpy-2.3.5-cp312-cp312-win_amd64.whl (12.8 MB)\n", - " ---------------------------------------- 0.0/12.8 MB ? eta -:--:--\n", - " ---------- ----------------------------- 3.4/12.8 MB 25.2 MB/s eta 0:00:01\n", - " ------------------------------- -------- 10.0/12.8 MB 28.2 MB/s eta 0:00:01\n", - " ---------------------------------------- 12.8/12.8 MB 25.0 MB/s 0:00:00\n", - "Installing collected packages: numpy\n", - "Successfully installed numpy-2.3.5\n", + "Requirement already satisfied: numpy in c:\\github\\python\\.venv\\lib\\site-packages (2.3.5)\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } @@ -317,7 +309,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 11, "metadata": { "id": "3TYo0-1SDLrd" }, @@ -326,15 +318,23 @@ "name": "stdout", "output_type": "stream", "text": [ - "60\n" + "Min array length: 60\n", + "Max array length: 60\n", + "Mean array length: 60\n" ] } ], "source": [ "# Test it out on the data file we read in and make sure the size is what we expect i.e., 60\n", "# Your output for the first file should be 60\n", + "# Test all three operations\n", "data_min = patient_summary(all_paths[0], 'min')\n", - "print(len(data_min))" + "data_max = patient_summary(all_paths[0], 'max')\n", + "data_mean = patient_summary(all_paths[0], 'mean')\n", + "\n", + "print(f\"Min array length: {len(data_min)}\")\n", + "print(f\"Max array length: {len(data_max)}\")\n", + "print(f\"Mean array length: {len(data_mean)}\")" ] }, { @@ -392,7 +392,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": { "id": "_svDiRkdIwiT" }, @@ -415,33 +415,65 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": { "id": "LEYPM5v4JT0i" }, "outputs": [], "source": [ "# Define your function `detect_problems` here\n", + "import os\n", "\n", "def detect_problems(file_path):\n", " #YOUR CODE HERE: Use patient_summary() to get the means and check_zeros() to check for zeros in the means\n", " means = patient_summary(file_path, 'mean')\n", + " filename = os.path.basename(file_path)\n", " has_zeros = check_zeros(means)\n", " if has_zeros:\n", - " print(\"Warning: At least one patient has a mean inflammation of 0.\")\n", + " print(f\"{filename}: True | Warning: At least one patient in has a mean inflammation of 0.\")\n", "\n", - " return" + " return f\"{filename}: False\"" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "inflammation_01.csv: False\n", + "inflammation_02.csv: False\n", + "inflammation_04.csv: False\n", + "inflammation_05.csv: False\n", + "inflammation_06.csv: False\n", + "inflammation_07.csv: False\n", + "inflammation_08.csv: True | Warning: At least one patient in has a mean inflammation of 0.\n", + "inflammation_08.csv: False\n", + "inflammation_09.csv: False\n", + "inflammation_10.csv: False\n", + "inflammation_11.csv: True | Warning: At least one patient in has a mean inflammation of 0.\n", + "inflammation_11.csv: False\n", + "inflammation_12.csv: False\n" + ] + } + ], "source": [ "# Test out your code here\n", "# Your output for the first file should be False\n", - "print(detect_problems(all_paths[0]))" + "print(detect_problems(all_paths[0]))\n", + "print(detect_problems(all_paths[1]))\n", + "print(detect_problems(all_paths[3]))\n", + "print(detect_problems(all_paths[4]))\n", + "print(detect_problems(all_paths[5]))\n", + "print(detect_problems(all_paths[6]))\n", + "print(detect_problems(all_paths[7]))\n", + "print(detect_problems(all_paths[8]))\n", + "print(detect_problems(all_paths[9]))\n", + "print(detect_problems(all_paths[10]))\n", + "print(detect_problems(all_paths[11]))\n" ] }, {