diff --git a/UFCFVQ-15-M_Programming_Task_1_submit.ipynb b/UFCFVQ-15-M_Programming_Task_1_submit.ipynb
index 801e6fab0097532bf987b8c663188054f572bef6..9d4d2e7392662aacc6c5d17cf070600db98f5175 100644
--- a/UFCFVQ-15-M_Programming_Task_1_submit.ipynb
+++ b/UFCFVQ-15-M_Programming_Task_1_submit.ipynb
@@ -486,76 +486,11 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "##### <b>`Pseudocode:`</b> \n",
- "\n",
- "\n",
- "<font color = red> Questions: </font> \n",
- "\n",
- "* are there any limitations to character usage - probably not\n",
- "* what is the source of the list of tuples? - probably doesn't matter - i.e. output from FR5 or variable storing list of tuples or list of tuples\n",
- "* columns to include?? - not sure what this means yet\n",
- "\n",
- "* doesn't the list of tuples parameter determine which columns are included? \n",
- " * may need to clarify this!\n",
- "\n",
- "- <b> TBD </b>\n",
- "\n",
- "<b>`Input:`</b> \n",
- "\n",
- "* list of tuples, e.g.\n",
- " * var1, var1, pcc11\n",
- " * var1, var2, pcc12\n",
- " * var1, var3, pcc13\n",
- " * var1, var4, pcc14\n",
- " * var2, var3, pcc23\n",
- " * var2, var4, pcc\n",
- " * var3, var4, pcc\n",
- " * var4, var4, pcc\n",
- "\n",
- "| | | | |\n",
- "|----|-----|-----|-----|\n",
- "| |var1 |var2 |var3 |\n",
- "|var1|pcc11|pcc12|pcc13|\n",
- "|var2|pcc21|pcc22|pcc23|\n",
- "|var3|pcc31|pcc32|pcc33|\n",
- "\n",
- "tuple = [(var1, var1, pcc11), (var1, var2, pcc12)]\n",
- "variable list = [var1, var2, var3]\n",
- "\n",
- "row header = iterate over variable list\n",
- "\n",
- "\n",
- "\n",
- "\n",
- "\n",
- "<b>`Parameters:` </b> \n",
- "* source of list of correlation coefficient tuples\n",
- "* border character to use\n",
- "* columns to include\n",
- "\n",
- "<b>`Output:`</b>\n",
- "\n",
- "* nicely printed ascii / dot matrix style table\n",
- "* formatted\n",
- "* padded / spaced\n",
- "* legible\n",
- "* footer??\n",
- "* title??\n",
- "\n",
- "<b>`Steps: `</b>\n",
- "\n",
- "1. No idea, yet...read about string formatting, probably.\n",
- "2. list of tuples\n",
- " * get variables into list (for header row and first element of each data row)\n",
- "3. enumerate over variable list for header row\n",
- "4. maybe get data into the right format to iterate over rows\n",
- "\n",
- "first unique element of each tuple = column headers\n",
- "iterate over elements 2, 3 for each tuple to print table\n",
- "\n",
+ "DELETE this cell and the next cell before submitting\n",
"\n",
+ "TODO\n",
"\n",
- "READ : https://docs.python.org/3/library/string.html#formatspec"
+ "Test with FR5 output\n"
]
},
{
@@ -564,323 +499,115 @@
"metadata": {},
"outputs": [],
"source": [
- "#test tuple based on appendix example\n",
+ "#DELETE THIS CELL BEFORE SUBMISSION\n",
+ "# \n",
+ "# test tuple based on appendix example\n",
"\n",
"tup_list = [('Glucose', 'Glucose', 1), ('BP', 'Glucose', 0.1429), ('BMI', 'Glucose', 0.0584), ('Age', 'Glucose', 0.5328), ('Glucose','BP', 0.1429), ('BP', 'BP', 1), ('BMI', 'BP', -0.4522), ('Age', 'BP', 0.4194), ('Glucose', 'BMI', 0.0584), ('BP', 'BMI', -0.4522), ('BMI', 'BMI', 1), ('Age', 'BMI', -0.3847), ('Glucose', 'Age', 0.5328), ('BP', 'Age', 0.4194), ('BMI', 'Age', -0.3847), ('Age', 'Age', 1)]"
]
},
{
"cell_type": "code",
- "execution_count": 88,
+ "execution_count": 251,
"metadata": {},
"outputs": [],
"source": [
- "# step by step building top of table\n",
- "\n",
- "def table_printer(tup_list, columns = sorted(set([x[0] for x in tup_list])), pad_char = '*'):\n",
+ "def max_col_width(tup_list):\n",
" '''\n",
- " Function which takes a list of tuples, optional padding character, and columns (??) and prints a the output as a table'''\n",
- "\n",
- " col_headers = sorted(set([x[0] for x in tup_list])) # create list of unique column headers\n",
- " row_headers = sorted(set([x[1] for x in tup_list])) # create list of unique row headers (same as cols)\n",
- "\n",
- "\n",
- " \n",
- " table_str = ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' # first table border\n",
- " table_str += ' ' * 15 # add 15 spaces to start table string\n",
- "\n",
- " for col in col_headers:\n",
- " table_str += f\"{col:^15}\" # add each column header to start table string\n",
- " table_str += '\\n' # add new line after column headers\n",
- " table_str += ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' #\n",
- "\n",
- " for row in row_headers:\n",
- " table_str += f\"{row:^15}\"+pad_char # add row header to table string\n",
- " for col in col_headers:\n",
- " # Get the corresponding value (3rd element of tuple) for the current row and column; if no value, use '-'\n",
- " r_val = next((x[2] for x in tup_list if x[0] == col and x[1] == row), '-') \n",
- " table_str += f\"{r_val:^15}\"+pad_char # add r_val to table string\n",
- " \n",
- " table_str += '\\n' # add new line after each row\n",
- " table_str += ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' # add bottom of table to match top\n",
+ " Function to calculate the maximum column width for a list of tuples'''\n",
+ " max_cols = 0\n",
+ " for row in tup_list:\n",
+ " max_cols = max(max_cols, len(row))\n",
"\n",
- " print(table_str)\n"
+ " col_widths = [0] * max_cols\n",
+ " for row in tup_list:\n",
+ " for col, value in enumerate(row):\n",
+ " col_widths[col] = max(col_widths[col], len(str(value)))\n",
+ " return max(col_widths)"
]
},
{
"cell_type": "code",
- "execution_count": 89,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " ************************************************************\n",
- " Age BMI BP Glucose \n",
- " ************************************************************\n",
- " Age * 1 * -0.3847 * 0.4194 * 0.5328 *\n",
- " BMI * -0.3847 * 1 * -0.4522 * 0.0584 *\n",
- " BP * 0.4194 * -0.4522 * 1 * 0.1429 *\n",
- " Glucose * 0.5328 * 0.0584 * 0.1429 * 1 *\n",
- " ************************************************************\n",
- "\n"
- ]
- }
- ],
- "source": [
- "table_printer(tup_list, '+')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "TODO\n",
- "\n",
- "table design with string formatting:\n",
- "get max column width and use in the format string\n",
- "* extend the second annd last borders to cover whole table\n",
- "* incorporate the last row border character so that it is aligned\n",
- "* print a footer?\n",
- "\n",
- "new parameter - columns to include? default should be all columns\n",
- "- is this arguments, keyword arguments, or both? investigate and test\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 98,
+ "execution_count": 254,
"metadata": {},
"outputs": [],
"source": [
- "# step by step building top of table\n",
- "\n",
- "def table_printer_with_col_option(tup_list, *col_headers, pad_char = '*'):\n",
+ "def FR6_print_table(tup_list, *col_headers, pad_char = '*'):\n",
+ " '''\n",
+ " Function which takes a list of tuples, columns to include (as *arguments) and optional single padding character (defaulted to '*') as parameters. The padding character is used to create a table with a border.\n",
" '''\n",
- " Function which takes a list of tuples, optional padding character, and columns (??) and prints a the output as a table'''\n",
"\n",
+ " # if no column headers are provided, use all unique column headers from tup_list\n",
" if not col_headers:\n",
" col_headers = sorted(set([x[0] for x in tup_list]))\n",
" else:\n",
" col_headers = col_headers\n",
- "\n",
+ " # create list of unique row headers (same as cols)\n",
" row_headers = col_headers\n",
- " #row_headers = sorted(set([x[1] for x in tup_list])) # create list of unique row headers (same as cols)\n",
- "\n",
- "\n",
" \n",
- " table_str = ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' # first table border\n",
- " table_str += ' ' * 15 # add 15 spaces to start table string\n",
+ " # calculate maximum column width in the data\n",
+ " max_width = int(max_col_width(tup_list) * 3)\n",
+ " \n",
+ " # create table string with top border based on padding character and maximum column width\n",
+ " table_str = ' ' * max_width + pad_char * (max_width * (len(col_headers))) + pad_char * (len(col_headers)+1)+ '\\n' \n",
+ " table_str += ' ' * max_width \n",
"\n",
+ " # add column headers to table string, using padding character and maximum column width\n",
" for col in col_headers:\n",
- " table_str += f\"{col:^15}\" # add each column header to start table string\n",
- " table_str += '\\n' # add new line after column headers\n",
- " table_str += ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' #\n",
+ " table_str += f\"{col:^{max_width+1}}\" \n",
+ " \n",
+ " table_str += '\\n' \n",
+ " table_str += ' ' * max_width + pad_char * (max_width * (len(col_headers))) + pad_char * (len(col_headers)+1)+'\\n' \n",
"\n",
+ " # add row headers and values to table string, using padding character and maximum column width\n",
" for row in row_headers:\n",
- " table_str += f\"{row:^15}\"+pad_char # add row header to table string\n",
- " for col in col_headers:\n",
- " # Get the corresponding value (3rd element of tuple) for the current row and column; if no value, use '-'\n",
+ " table_str += f\"{row:^{max_width}}\"+pad_char \n",
+ " \n",
+ " # Get the corresponding value (3rd element of tuple) for the current row and column; if no value, use '-'\n",
+ " for col in col_headers: \n",
" r_val = next((x[2] for x in tup_list if x[0] == col and x[1] == row), '-') \n",
- " table_str += f\"{r_val:^15}\"+pad_char # add r_val to table string\n",
+ " \n",
+ " # if value is positive, add a space to the left of the value to keep the table aligned\n",
+ " if r_val >= 0:\n",
+ " table_str += f\" {r_val:^{max_width-1}}\" + pad_char \n",
+ " else:\n",
+ " table_str += f\"{r_val:^{max_width}}\" + pad_char\n",
" \n",
- " table_str += '\\n' # add new line after each row\n",
- " table_str += ' ' * 15 + pad_char * (15 * len(col_headers)) + '\\n' # add bottom of table to match top\n",
+ " table_str += '\\n' \n",
"\n",
- " print(table_str)\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 102,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n",
- " Glucose Age BMI \n",
- " %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n",
- " Glucose % 1 % 0.5328 % 0.0584 %\n",
- " Age % 0.5328 % 1 % -0.3847 %\n",
- " BMI % 0.0584 % -0.3847 % 1 %\n",
- " %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%\n",
- "\n"
- ]
- }
- ],
- "source": [
- "table_printer_with_col_option(tup_list, 'Glucose', 'Age', 'BMI', pad_char = '%')\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 152,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Glucose#Glucose# 1#\n",
- " BP#Glucose# 0.1429#\n",
- " BMI#Glucose# 0.0584#\n",
- " Age#Glucose# 0.5328#\n",
- "Glucose# BP# 0.1429#\n",
- " BP# BP# 1#\n",
- " BMI# BP#-0.4522#\n",
- " Age# BP# 0.4194#\n",
- "Glucose# BMI# 0.0584#\n",
- " BP# BMI#-0.4522#\n",
- " BMI# BMI# 1#\n",
- " Age# BMI#-0.3847#\n",
- "Glucose# Age# 0.5328#\n",
- " BP# Age# 0.4194#\n",
- " BMI# Age#-0.3847#\n",
- " Age# Age# 1#\n"
- ]
- }
- ],
- "source": [
- "data = tup_list\n",
- "\n",
- "max_cols = 0\n",
- "for row in data:\n",
- " max_cols = max(max_cols, len(row))\n",
- "\n",
- "col_widths = [0] * max_cols\n",
- "for row in data:\n",
- " for col, value in enumerate(row):\n",
- " col_widths[col] = max(col_widths[col], len(str(value)))\n",
- "\n",
- "for col, value in enumerate(data[0]):\n",
- " print(str(value).rjust(col_widths[col]), end='#')\n",
- "print()\n",
+ " # add bottom border to table string, using padding character and maximum column width \n",
+ " table_str += ' ' * max_width + pad_char * max_width * len(col_headers) + pad_char * (len(col_headers)+1)+ '\\n\\n' \n",
+ " \n",
+ " # add caption for table\n",
+ " table_str += ' ' * max_width + \"Pearson's Correlation Coefficient for %s\" % (col_headers,)\n",
"\n",
- " # Print the data rows\n",
- "for row in data[1:]:\n",
- " for col, value in enumerate(row):\n",
- " print(str(value).rjust(col_widths[col]), end='#')\n",
- " print()\n",
- "\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 143,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "3\n",
- "[7, 7, 7]\n"
- ]
- }
- ],
- "source": [
- "print(max_cols)\n",
- "print(col_widths)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 132,
- "metadata": {},
- "outputs": [],
- "source": [
- "def print_table(data, padding):\n",
- " # First, find the maximum number of columns in any row\n",
- " max_cols = 0\n",
- " for row in data:\n",
- " max_cols = max(max_cols, len(row))\n",
- "\n",
- " # Then, for each column, find the maximum width of any value in that column\n",
- " col_widths = [0] * max_cols\n",
- " for row in data:\n",
- " for col, value in enumerate(row):\n",
- " col_widths[col] = max(col_widths[col], len(str(value)))\n",
- "\n",
- " # Print the header row\n",
- " for col, value in enumerate(data[0]):\n",
- " print(str(value).rjust(col_widths[col]), end=padding)\n",
- " print()\n",
- "\n",
- " # Print a horizontal line\n",
- " for col, width in enumerate(col_widths):\n",
- " print(\"-\" * width, end=padding)\n",
- " print()\n",
- "\n",
- " # Print the data rows\n",
- " for row in data[1:]:\n",
- " for col, value in enumerate(row):\n",
- " print(str(value).rjust(col_widths[col]), end=padding)\n",
- " print()\n",
- "\n",
- " # Print a horizontal line\n",
- " for col, width in enumerate(col_widths):\n",
- " print(\"-\" * width, end=padding)\n",
- " print()\n",
- "\n",
- " # Print the total row\n",
- " print(\"Total\", end=padding)\n",
- " for col in range(1, max_cols):\n",
- " col_sum = 0\n",
- " for row in data[1:]:\n",
- " if col < len(row):\n",
- " col_sum += row[col]\n",
- " print(str(col_sum).rjust(col_widths[col]), end=padding)\n",
- " print()"
+ " # print table string\n",
+ " print(table_str)\n"
]
},
{
"cell_type": "code",
- "execution_count": 139,
+ "execution_count": 255,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "GlucosexGlucosex 1x\n",
- "-------x-------x-------x\n",
- " BPxGlucosex 0.1429x\n",
- " BMIxGlucosex 0.0584x\n",
- " AgexGlucosex 0.5328x\n",
- "Glucosex BPx 0.1429x\n",
- " BPx BPx 1x\n",
- " BMIx BPx-0.4522x\n",
- " Agex BPx 0.4194x\n",
- "Glucosex BMIx 0.0584x\n",
- " BPx BMIx-0.4522x\n",
- " BMIx BMIx 1x\n",
- " Agex BMIx-0.3847x\n",
- "Glucosex Agex 0.5328x\n",
- " BPx Agex 0.4194x\n",
- " BMIx Agex-0.3847x\n",
- " Agex Agex 1x\n",
- "-------x-------x-------x\n",
- "Totalx"
- ]
- },
- {
- "ename": "TypeError",
- "evalue": "unsupported operand type(s) for +=: 'int' and 'str'",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[1;32mIn [139], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m print_table(tup_list,\u001b[39m\"\u001b[39;49m\u001b[39mx\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
- "Cell \u001b[1;32mIn [132], line 40\u001b[0m, in \u001b[0;36mprint_table\u001b[1;34m(data, padding)\u001b[0m\n\u001b[0;32m 38\u001b[0m \u001b[39mfor\u001b[39;00m row \u001b[39min\u001b[39;00m data[\u001b[39m1\u001b[39m:]:\n\u001b[0;32m 39\u001b[0m \u001b[39mif\u001b[39;00m col \u001b[39m<\u001b[39m \u001b[39mlen\u001b[39m(row):\n\u001b[1;32m---> 40\u001b[0m col_sum \u001b[39m+\u001b[39;49m\u001b[39m=\u001b[39;49m row[col]\n\u001b[0;32m 41\u001b[0m \u001b[39mprint\u001b[39m(\u001b[39mstr\u001b[39m(col_sum)\u001b[39m.\u001b[39mrjust(col_widths[col]), end\u001b[39m=\u001b[39mpadding)\n\u001b[0;32m 42\u001b[0m \u001b[39mprint\u001b[39m()\n",
- "\u001b[1;31mTypeError\u001b[0m: unsupported operand type(s) for +=: 'int' and 'str'"
+ " +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++\n",
+ " Age BMI BP \n",
+ " +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++\n",
+ " Age + 1 + -0.3847 + 0.4194 +\n",
+ " BMI + -0.3847 + 1 + -0.4522 +\n",
+ " BP + 0.4194 + -0.4522 + 1 +\n",
+ " +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++\n",
+ "\n",
+ " Pearson's Correlation Coefficient for ('Age', 'BMI', 'BP')\n"
]
}
],
"source": [
- "print_table(tup_list,\"x\")"
+ "FR6_print_table(tup_list, 'Age', 'BMI', 'BP', pad_char = '+')\n"
]
},
{