From 367168400224b59040daa0ef34e5d0c1b872cdcb Mon Sep 17 00:00:00 2001
From: am2-liyanaarac <akash2.liyanaarachchi@live.uwe.ac.uk>
Date: Tue, 4 Apr 2023 15:37:19 +0100
Subject: [PATCH] FR6 completed but padding changing with different column
sizes
---
UFCFVQ-15-M_Python_Programming_Template.ipynb | 158 +++++++++++++-----
1 file changed, 117 insertions(+), 41 deletions(-)
diff --git a/UFCFVQ-15-M_Python_Programming_Template.ipynb b/UFCFVQ-15-M_Python_Programming_Template.ipynb
index 0dbc269..bb72a2e 100644
--- a/UFCFVQ-15-M_Python_Programming_Template.ipynb
+++ b/UFCFVQ-15-M_Python_Programming_Template.ipynb
@@ -51,7 +51,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 29,
"metadata": {
"deletable": false
},
@@ -65,28 +65,21 @@
}
],
"source": [
- "def geometric_mean(numbers):\n",
+ "def geometric_mean(num_lst):\n",
" \"\"\"\n",
" Calculate the geometric mean of a list of numbers.\n",
- "\n",
- " Parameters:\n",
- " numbers (list): A list of positive integers or floats.\n",
- "\n",
- " Returns:\n",
- " float: The geometric mean of the numbers in the list.\n",
+ " :param num_lst: A list of positive integers or floats.\n",
+ " :returns float: The geometric mean of the numbers in the list.\n",
" \"\"\"\n",
" # Initialize the product of the numbers\n",
" product = 1\n",
- " # Length of the list\n",
- " num_elements = len(numbers)\n",
"\n",
" # Iterate through the list of numbers and multiply each number\n",
- " for number in numbers:\n",
+ " for number in num_lst:\n",
" product *= number\n",
"\n",
- " # Calculate the nth root of the product\n",
- " geometric_mean_result = product ** (1 / num_elements)\n",
- " return geometric_mean_result\n",
+ " # Calculate the nth root of the product and return it\n",
+ " return product ** (1 / len(num_lst))\n",
"\n",
"# Test the function with the provided list of numbers\n",
"test_number_list = [64, 9, 90, 28, 46, 95, 34, 28, 86, 62, 14, 77, 99, 80,\n",
@@ -119,7 +112,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 30,
"metadata": {
"deletable": false
},
@@ -208,7 +201,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 31,
"metadata": {
"deletable": false
},
@@ -222,7 +215,7 @@
}
],
"source": [
- "def read_all_csv_data(file_name, conversion_indicators) -> dict:\n",
+ "def read_all_csv_data(file_name, conversion_indicators):\n",
" \"\"\"\n",
" This function will return all columns data as a dictionary\n",
" :param file_name: CSV file path\n",
@@ -251,9 +244,9 @@
"\n",
"file_path = 'task1.csv'\n",
"conversion_flags = [True, True, True, True, True, True, True, True, True, True]\n",
- "data_dict = read_all_csv_data(file_path, conversion_flags)\n",
+ "all_csv_data = read_all_csv_data(file_path, conversion_flags)\n",
"\n",
- "print(data_dict)"
+ "print(all_csv_data)"
]
},
{
@@ -287,7 +280,7 @@
},
{
"cell_type": "code",
- "execution_count": 21,
+ "execution_count": 32,
"outputs": [
{
"name": "stdout",
@@ -309,10 +302,10 @@
" for i, val in enumerate(sorted(lst), 1):\n",
" ranks.setdefault(val, []).append(i)\n",
"\n",
+ " # get the average rank of each item using dictionary comprehension\n",
" avg_ranks = {v: sum(r) / len(r) for v, r in ranks.items()}\n",
"\n",
- " ranked_list = [avg_ranks[val] for val in lst]\n",
- " return ranked_list\n",
+ " return [avg_ranks[val] for val in lst]\n",
"\n",
"\n",
"def sm_correlation_coefficient(data1, data2):\n",
@@ -332,16 +325,15 @@
" # get the sum of squared differences of each item in both lists\n",
" sum_sqr_diff = 0\n",
" for i in range(len(ranked_data1)):\n",
- "\n",
" diff = ranked_data1[i] - ranked_data2[i] # differences of each list item\n",
" sqr = diff ** 2 # squared differences\n",
" sum_sqr_diff += sqr # get the sum of each squared differences\n",
"\n",
" # Calculate the Spear-man's Rank Correlation Coefficient using the formula\n",
" n = len(data1)\n",
- " correlation = 1 - (6 * sum_sqr_diff) / (n * (n ** 2 - 1))\n",
+ " correlation_coefficient = 1 - (6 * sum_sqr_diff) / (n * (n ** 2 - 1))\n",
"\n",
- " return correlation\n",
+ " return correlation_coefficient\n",
"\n",
"\n",
"# Read two columns of data from the CSV file\n",
@@ -371,7 +363,7 @@
},
{
"cell_type": "code",
- "execution_count": 25,
+ "execution_count": 33,
"metadata": {
"deletable": false
},
@@ -385,16 +377,16 @@
}
],
"source": [
- "def generate_correlation_coefficients(csv_file_path):\n",
+ "def generate_all_correlation_coefficients(csv_file_path):\n",
" # Read the data from the CSV file\n",
- " con_flags = [True, True, True, True, True, True, True, True, True, True]\n",
- " column_data = read_all_csv_data(csv_file_path, con_flags)\n",
+ " conversion_indicators = [True, True, True, True, True, True, True, True, True, True]\n",
+ " all_column_data = read_all_csv_data(csv_file_path, conversion_indicators)\n",
"\n",
" # Get the column names\n",
- " column_names = list(column_data.keys())\n",
+ " column_names = list(all_column_data.keys())\n",
"\n",
" # Initialize an empty list to store the correlation coefficients\n",
- " correlation_coefficients = []\n",
+ " all_correlation_coefficients = []\n",
"\n",
" # Iterate through all pairs of columns\n",
" for i in range(len(column_names)):\n",
@@ -403,23 +395,25 @@
" continue # skip the comparison of the same column with itself\n",
"\n",
" col1_name = column_names[i]\n",
- " col1_data = column_data[col1_name]\n",
+ " col1_data = all_column_data[col1_name]\n",
"\n",
" col2_name = column_names[j]\n",
- " col2_data = column_data[col2_name]\n",
+ " col2_data = all_column_data[col2_name]\n",
"\n",
" # Calculate the Spearman's Rank Correlation Coefficient for the current pair of columns\n",
" try:\n",
- " coefficient = sm_correlation_coefficient(col1_data, col2_data)\n",
- " correlation_coefficients.append((col1_name, col2_name, coefficient))\n",
+ " sm_cor_coefficient = sm_correlation_coefficient(col1_data, col2_data)\n",
+ " all_correlation_coefficients.append((col1_name, col2_name, sm_cor_coefficient))\n",
" except ValueError as e:\n",
- " print(f\"Error occured: {e}\")\n",
+ " print(f\"A value error occurred: {e}\")\n",
+ " except Exception as ex:\n",
+ " print(f\"An error occurred: {ex}\")\n",
"\n",
- " return correlation_coefficients\n",
+ " return all_correlation_coefficients\n",
"\n",
"# Test the generate_correlation_coefficients function\n",
"file_path = 'task1.csv'\n",
- "result = generate_correlation_coefficients(file_path)\n",
+ "result = generate_all_correlation_coefficients(file_path)\n",
"print(result)\n"
]
},
@@ -444,15 +438,97 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 187,
"metadata": {
"deletable": false
},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$\n",
+ " $ age $ pop $ share_white $ share_black $\n",
+ "$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$\n",
+ "$ age $ - $ 0.0084 $ 0.2207 $ -0.1034 $\n",
+ "$ pop $ 0.0084 $ - $ 0.0767 $ -0.1339 $\n",
+ "$ share_white $ 0.2207 $ 0.0767 $ - $ -0.4917 $\n",
+ "$ share_black $ -0.1034 $ -0.1339 $ -0.4917 $ - $\n",
+ "$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$\n"
+ ]
+ }
+ ],
"source": [
- "# replace with your code"
+ "def print_table(correlations, border_char, columns):\n",
+ " # Find the length of the longest string in the list and add constant to define cell length\n",
+ " longest_string_length = len(max(columns, key=len))\n",
+ " max_cell_length = longest_string_length + 5\n",
+ "\n",
+ " # print top boarder\n",
+ " # Initialize a variable to hold the sum of string lengths starts with 1 to hold the cell gap.\n",
+ " sum_col_lengths = 1\n",
+ "\n",
+ " # Loop over each string in the list and add its length to the running total\n",
+ " for name in columns:\n",
+ " sum_col_lengths += len(name)\n",
+ "\n",
+ " sum_col_lengths += len(columns) * 7\n",
+ " print(\" \" * max_cell_length + \"$\" * sum_col_lengths)\n",
+ "\n",
+ " # print the column names\n",
+ " print(\" \" * max_cell_length, end=\"\")\n",
+ " for name in columns:\n",
+ " print(border_char + \" \" * 3 + name + \" \" * 3 , end=\"\")\n",
+ " print(\"$\")\n",
+ "\n",
+ " # print header separator\n",
+ " print(\"$\" * (max_cell_length + sum_col_lengths))\n",
+ "\n",
+ " # print the correlation coefficients\n",
+ " for i, value in enumerate(columns):\n",
+ " string_len_diff = longest_string_length - len(value) + 5\n",
+ " space_count = int(string_len_diff / 2)\n",
+ "\n",
+ " if len(value) % 2 == 0:\n",
+ " print(border_char + space_count * \" \" + value + (space_count - 1) * \" \", end=\"\")\n",
+ " else:\n",
+ " print(border_char + space_count * \" \" + value + space_count * \" \", end=\"\")\n",
+ "\n",
+ " for col_name in columns:\n",
+ " if value == col_name:\n",
+ " cell_space = int(((len(col_name) + 7 ) / 2) -1) * \" \"\n",
+ " print(border_char + cell_space + \"-\" + cell_space, end=\"\")\n",
+ "\n",
+ " else:\n",
+ " for element in correlations:\n",
+ " if element[0] == value and element[1] == col_name:\n",
+ " correlation_coefficient = round(element[2], 4)\n",
+ " cell_space = (len(col_name)) // 2 * \" \"\n",
+ " if correlation_coefficient > 0:\n",
+ " print(border_char + \" \" +cell_space + str(correlation_coefficient) + cell_space, end=\"\")\n",
+ " else:\n",
+ " print(border_char +cell_space + str(correlation_coefficient) + cell_space, end=\"\")\n",
+ "\n",
+ "\n",
+ " print(\"$\")\n",
+ "\n",
+ " # print footer\n",
+ " # print header separator\n",
+ " print(\"$\" * (max_cell_length + sum_col_lengths))\n",
+ "\n",
+ "\n",
+ "file_path = 'task1.csv'\n",
+ "columns_to_include = ['age','pop', 'share_white', 'share_black']\n",
+ "print_table(generate_all_correlation_coefficients(file_path), '$', columns_to_include)"
]
},
+ {
+ "cell_type": "markdown",
+ "source": [],
+ "metadata": {
+ "collapsed": false
+ }
+ },
{
"cell_type": "markdown",
"metadata": {
--
GitLab