diff --git a/UFCFVQ-15-M Programming Task 1.ipynb b/UFCFVQ-15-M Programming Task 1.ipynb
index 7709324229324a10a6ff7dba8355f4a0b5729f26..e3d2c151008db46337be740d2fcbb1389dc074df 100644
--- a/UFCFVQ-15-M Programming Task 1.ipynb
+++ b/UFCFVQ-15-M Programming Task 1.ipynb
@@ -21,7 +21,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -51,7 +51,7 @@
"#Converting all string numbers to (integer)\n",
"List = list(map(int, ConvertToList))\n",
"#Now all numbers are integer niside the list e.g [148, 85, 183]\n",
- "print(f'3) The items inside {type(List)} is {type(List[0])} | Now its a list of integer') "
+ "print(f'3) The items inside {type(List)} is {type(List[0])} | Now its a list of integer')"
]
},
{
@@ -63,31 +63,31 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "The mean of the list = 120.89453125\n"
+ "The mean of the datan list is 120.89453125\n"
]
}
],
"source": [
- "#function to get the mean of a python list\n",
+ "#function to get the mean of a given python list\n",
"def meanFinder(List):\n",
- " #assining the varivale to be global so it can be called any were else (as it has been called in FR1.7)\n",
+ " #assining the variable to be global so it can be called any were else (as it has been called in FR1.7)\n",
" global ListMean\n",
- " \n",
+ "\n",
" #Find the mean of the list using the mathematical mean equation\n",
" ListMean = sum(List)/len(List)\n",
- " \n",
+ "\n",
" #Rturn The result\n",
" return ListMean\n",
"\n",
"#Calling the function and passing the >> List << argument to it \n",
- "print(f'The mean of the list = {meanFinder(List)}')"
+ "print(f'The mean of the datan list is {meanFinder(List)}')"
]
},
{
@@ -107,19 +107,19 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Standard Devision of the list = 31.95179590820272\n"
+ "Standard Devision of the data list is 31.95179590820272\n"
]
}
],
"source": [
- "#Function to find the standard deviation\n",
+ "#Function to find the standard deviation of a given python list\n",
"def StdDevFinder(List): \n",
" #Find the variance among the list using its mathematical equation\n",
" # (Square each deviation from the mean & Calculate the variance)\n",
@@ -129,9 +129,8 @@
" #Rturn The result\n",
" return STD_DEV\n",
"\n",
- "\n",
"#Calling the function and passing the >> List << argument to it \n",
- "print(f'Standard Devision of the list = {StdDevFinder(List)}')"
+ "print(f'Standard Devision of the data list is {StdDevFinder(List)}')"
]
},
{
@@ -151,15 +150,15 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "The minimum number in the list = 0\n",
- "The maximum in the list = 199\n"
+ "The minimum number in the data list is 0\n",
+ "The maximum in the data list is 199\n"
]
}
],
@@ -177,9 +176,9 @@
"\n",
" \n",
"#Calling the functions and passing the >> List << argument to it \n",
- "print(f'The minimum number in the list = {MinFinder(List)}')\n",
+ "print(f'The minimum number in the data list is {MinFinder(List)}')\n",
"\n",
- "print(f'The maximum in the list = {MaxFinder(List)}')\n"
+ "print(f'The maximum in the data list is {MaxFinder(List)}')\n"
]
},
{
@@ -200,7 +199,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
@@ -211,11 +210,11 @@
" ListNumber = len(List)\n",
" #Multiplying the length with the percentile number and dividing it by 100 (percentile equation) \n",
" Listpercentile = ListNumber * percentile / 100\n",
- " #If the number inside the (List Percentile) is integer, sort it and return it to (List Percentile list)\n",
+ " #If the number inside the (ListPercentile) is integer, sort it and return it to (List Percentile list)\n",
" if Listpercentile.is_integer():\n",
" Listpercentile = sorted(List)[int(Listpercentile)]\n",
" return Listpercentile\n",
- " #else, remove it from (List Percentile list)\n",
+ " #else, remove it from (ListPercentile list)\n",
" else:\n",
" Listpercentile = sorted(List)[int(round(Listpercentile)) -1]\n",
" return Listpercentile"
@@ -230,7 +229,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -265,7 +264,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -300,7 +299,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 12,
"metadata": {},
"outputs": [
{
@@ -335,7 +334,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -391,15 +390,13 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "[+] File Size >>> 3.638 (KB) | 3638 Bytes | 0.003638 (MB)\n",
- "\n",
"[+] The data type is <class 'list'> and the numbers inside is <class 'int'>\n",
"\n",
"[+] The file content as shown:\n",
@@ -416,19 +413,9 @@
"ConvertToList = list(FileName.strip().split())\n",
"#Converting it to integer list\n",
"List = list(map(int, ConvertToList))\n",
- "\n",
- "#Finding the file size inside the computer memory\n",
- "def getSize(file):\n",
- " file.seek(0,2) #To count from the from the start of the file, and stop at the end.\n",
- " FileSize = file.tell() # To get file position\n",
- " #Print file size\n",
- " print(f'[+] File Size >>> {FileSize*0.001} (KB) | {FileSize} Bytes | {round(FileSize*0.000001,6)} (MB)\\n')\n",
" \n",
- "FileName = open('task1.dat','r')\n",
- "getSize(FileName)\n",
- "\n",
"print(f'[+] The data type is {type(List)} and the numbers inside is {type(List[0])}\\n')\n",
- "print(f\"[+] The file content as shown:\\n\\n{List[0:]}\")\n"
+ "print(f\"[+] The file content as shown:\\n\\n{List[:]}\")\n"
]
},
{
@@ -451,40 +438,12 @@
"metadata": {},
"source": [
"Following the given instruction in the appendix.A (output structure), this task has been created.\n",
- "To be visualised better, the data output has been limited to 10 in each row."
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "##### Explanation 1 Example for \"EachClmToList\"\n",
- "\n",
- "['A','B','C'],\n",
- "\n",
- "['1','2','3'],\n",
- "\n",
- "['4','5','6'],so on..\n",
- "\n",
- "Therfore EachClmToList[0] = ['A','1','4'..]\n",
- "\n",
- "##### Explanation 2\n",
- "For loop is created to reach out to every single data inside 'AppendTolist' in the range of the data length,\n",
- "(768) or (767) if we count from 0. To be able to do so, 2 for loop should be created as shown, one to count the number of\n",
- "columns which is (9) or 8 if we count the zero, and the other to count the number of data in each row.\n",
- "therefore it will start from [0][0].. [1][0].. [2][0] until it reaches [767][0] and switch to [0][1]..\n",
- "and continue until it reaches the last data in the file which is at [767][8].\n",
- "while so, the data (numbers) will be appended to a new list called 'EachClmToList'\n",
- "\n",
- "##### Explanation 3\n",
- "A mathematical operation to create a sublist of (each data under each line for the header ) to achieve exploration 1, therefore\n",
- "for every end of a line create a new list for the next line, and at the end, we will have a total of 9 lists that \n",
- "achieved to carry each column of data into one list "
+ "To be visualised better, the data output has been limited to 13 in each row."
]
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 60,
"metadata": {},
"outputs": [],
"source": [
@@ -492,7 +451,7 @@
"AppendTolist = [] #Creating an empty list to append all the CSV data inside it\n",
"ColumnHeader = [] #Creating an empty list to append the CSV Column Header (Name of each column)\n",
"\n",
- "#Refer to Explanation (1)\n",
+ "#Refer to Explanation (1) at the end\n",
"EachClmToList = [] #Creating an empty list to append Each column-row (each data under each line for the header ) \n",
"\n",
"'''\n",
@@ -504,28 +463,31 @@
" AppendTolist.append(data) #Append (adding) the new data into the 'AppendTolist' list\n",
"#print(AppendTolist[0:5])\n",
"\n",
- "#For loop to append only the first list >> [0] << of the 'AppendTolist', which is the columns header to another list.\n",
+ "#For loop to append only the first list >> [0] << of the 'AppendTolist', which is the header row (names).\n",
"for subList in AppendTolist[0]: \n",
" ColumnHeader.append(subList) #append to another list. \n",
- "#Removing the appended it from the main list 'AppendTolist'\n",
+ "#Removing the names row from the main list 'AppendTolist'\n",
"AppendTolist.remove(AppendTolist[0])\n",
"\n",
- "#Refer to Explanation (2) \n",
+ "#Refer to Explanation (2) at the end\n",
"for clmLen in range(len(ColumnHeader)): #9 aka 8 as it starts from 0\n",
" #print(ColumnHeader)\n",
" for RowLen in range(len(AppendTolist)):#768 aka 767 as it satrts from 0 \n",
- " #print(AppendTolist[767][8])\n",
+ " #print(AppendTolist[RowLen][clmLen])\n",
" EachClmToList.append(AppendTolist[RowLen][clmLen]) \n",
"#print(EachClmToList)\n",
"\n",
"#to avoid python errors, a new variable is created called 'numberOfDataInEach' that carries row length in each line.\n",
"numberOfDataInEach = len(AppendTolist)\n",
"\n",
- "#Refer to Explanation (3)\n",
+ "#Refer to Explanation (3) at the end\n",
"EachClmToList = [EachClmToList[x:x+numberOfDataInEach] for x in range(0, len(EachClmToList), numberOfDataInEach)]\n",
"\n",
"\n",
- "#As per as requested the data is stored in the memory and can be called later for analyzing"
+ "#As per as requested the data is stored in the memory and can be called later for analyzing\n",
+ "\n",
+ "#but for proven of successful output, the data can be printed out by uncommenting the next line\n",
+ "#print(ColumnHeader,EachClmToList[:][:])"
]
},
{
@@ -545,33 +507,33 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 71,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
- "\"Pregnancies\" : [6.0, 1.0, 8.0, 1.0, 0.0, 5.0, 3.0, 10.0, 2.0, 8.0]\n",
- "\"Glucose\" : [148.0, 85.0, 183.0, 89.0, 137.0, 116.0, 78.0, 115.0, 197.0, 125.0]\n",
- "\"BloodPressure\" : [72.0, 66.0, 64.0, 66.0, 40.0, 74.0, 50.0, 0.0, 70.0, 96.0]\n",
- "\"SkinThickness\" : [35.0, 29.0, 0.0, 23.0, 35.0, 0.0, 32.0, 0.0, 45.0, 0.0]\n",
- "\"Insulin\" : [0.0, 0.0, 0.0, 94.0, 168.0, 0.0, 88.0, 0.0, 543.0, 0.0]\n",
- "\"BMI\" : [33.6, 26.6, 23.3, 28.1, 43.1, 25.6, 31.0, 35.3, 30.5, 0.0]\n",
- "\"DiabetesPedigreeFunction\" : [0.627, 0.351, 0.672, 0.167, 2.288, 0.201, 0.248, 0.134, 0.158, 0.232]\n",
- "\"Age\" : [50.0, 31.0, 32.0, 21.0, 33.0, 30.0, 26.0, 29.0, 53.0, 54.0]\n",
- "\"Outcome\" : [1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 1.0]\n"
+ "\"Pregnancies\" : [6.0, 1.0, 8.0, 1.0, 0.0, 5.0, 3.0, 10.0, 2.0, 8.0, 4.0, 10.0, 10.0]\n",
+ "\"Glucose\" : [148.0, 85.0, 183.0, 89.0, 137.0, 116.0, 78.0, 115.0, 197.0, 125.0, 110.0, 168.0, 139.0]\n",
+ "\"BloodPressure\" : [72.0, 66.0, 64.0, 66.0, 40.0, 74.0, 50.0, 0.0, 70.0, 96.0, 92.0, 74.0, 80.0]\n",
+ "\"SkinThickness\" : [35.0, 29.0, 0.0, 23.0, 35.0, 0.0, 32.0, 0.0, 45.0, 0.0, 0.0, 0.0, 0.0]\n",
+ "\"Insulin\" : [0.0, 0.0, 0.0, 94.0, 168.0, 0.0, 88.0, 0.0, 543.0, 0.0, 0.0, 0.0, 0.0]\n",
+ "\"BMI\" : [33.6, 26.6, 23.3, 28.1, 43.1, 25.6, 31.0, 35.3, 30.5, 0.0, 37.6, 38.0, 27.1]\n",
+ "\"DiabetesPedigreeFunction\" : [0.627, 0.351, 0.672, 0.167, 2.288, 0.201, 0.248, 0.134, 0.158, 0.232, 0.191, 0.537, 1.441]\n",
+ "\"Age\" : [50.0, 31.0, 32.0, 21.0, 33.0, 30.0, 26.0, 29.0, 53.0, 54.0, 30.0, 34.0, 57.0]\n",
+ "\"Outcome\" : [1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 0.0, 1.0, 1.0, 0.0, 1.0, 0.0]\n"
]
}
],
"source": [
"#Creating function to construct the data structure and to call it after. \n",
- "def dataStrcuture():\n",
+ "def DataDemonstration():\n",
" for x in range(len(ColumnHeader)):\n",
- " print(f'\"{ColumnHeader[x]}\" : {list(map(float,EachClmToList[x][:10]))}') #numbers has been converted to float\n",
- " #Only 10 data have been printed to better visualize the result, for the whole result remove [:10], [:] or none\n",
- " #list(map(float,EachClmToList[x][:10]))\n",
- "dataStrcuture()"
+ " print(f'\"{ColumnHeader[x]}\" : {list(map(float,EachClmToList[x][:13]))}') #numbers has been converted to float\n",
+ " #Only 13 data have been printed to better visualize the result, for the whole result remove [:13], which will be\n",
+ " #list(map(float,EachClmToList[x]))\n",
+ "DataDemonstration()"
]
},
{
@@ -591,7 +553,7 @@
},
{
"cell_type": "code",
- "execution_count": 91,
+ "execution_count": 87,
"metadata": {},
"outputs": [
{
@@ -614,9 +576,10 @@
],
"source": [
"print('\"Stats\" : [\"Mean\",\"Stdev\", \"Min\", Max\",\"25%\",\"50%\",\"75%\"]\\n')\n",
- "#Calling the file \n",
- "def dataStrcuture():\n",
- " global data\n",
+ "\n",
+ "#function for Data Statistical\n",
+ "def DataStatistical():\n",
+ "\n",
" #Creating an empty list to append Each column-row (each data under each line for the header ) \n",
" ConvertdeToFloat = []\n",
"\n",
@@ -624,10 +587,8 @@
" for x in range(len(ColumnHeader)):\n",
" EachClmInListToFloat = list(map(float,EachClmToList[x][:]))\n",
" ConvertdeToFloat.append(EachClmInListToFloat)\n",
- " \n",
- " \n",
- " #Creating variables that contains the required information to create the data structure\n",
- " #and calling function that has been saved in memory before. \n",
+ "\n",
+ " #Creating variables that contains the required information to create the datas tatistical structure\n",
" \n",
" for x in range(len(ColumnHeader)):\n",
" data = [round(meanFinder(ConvertdeToFloat[x][:]),3),\n",
@@ -640,7 +601,7 @@
" ]\n",
" print(f'\"{ColumnHeader[x]}\" : {data}')\n",
" \n",
- "dataStrcuture()"
+ "DataStatistical()"
]
},
{
@@ -660,7 +621,7 @@
},
{
"cell_type": "code",
- "execution_count": 94,
+ "execution_count": 76,
"metadata": {},
"outputs": [
{
@@ -684,14 +645,16 @@
}
],
"source": [
- "#Calling the file \n",
- "def dataStrcuture():\n",
+ "#Function to print out a custom statistical table\n",
+ "def DataCustomStatistical():\n",
" \n",
+ " #DiabetesPedigreeFunction name is changed to DiabPedFnc as it takes a lot of space to print it out.\n",
" newList = [element.replace('DiabetesPedigreeFunction', 'DiabPedFnc') for element in ColumnHeader]\n",
" clmName = [newList]\n",
+ " \n",
" Status = [\"Mean\",\"Stdev\", \"Min\", \"Max\",\"25%\",\"50%\",\"75%\"]\n",
" format_row = \"{: >13} \" * (len(Status)+1)\n",
- " print(stars.rjust(121,'*'))\n",
+ " print(stars.rjust(121,'*')) #Printing the stars\n",
" print(format_row.format(\"Status\", *Status))\n",
" print(stars.rjust(121,'*'))\n",
"\n",
@@ -708,7 +671,7 @@
" #and calling function that has been saved in memory before.\n",
" \n",
" for x in range(len(ColumnHeader)):\n",
- "\n",
+ " \n",
" data = [[round(meanFinder(ConvertdeToFloat[x][:]),3),\n",
" round(StdDevFinder((ConvertdeToFloat[x][:])),3),\n",
" MaxFinder(ConvertdeToFloat[x][:]),\n",
@@ -720,13 +683,12 @@
"\n",
" format_row = \"{:>15}\" * (len(Status) + 1)\n",
" \n",
- " for names, row in zip(clmName, data):\n",
+ " for names, row in zip(clmName, data): #Printing the result out formatted to have an organized custom table\n",
" #print(team[x])\n",
" print(format_row.format(names[x], *row))\n",
"\n",
- "\n",
- "dataStrcuture()\n",
"stars = '*'\n",
+ "DataCustomStatistical()\n",
"print(stars.rjust(121,'*'))"
]
},
@@ -749,14 +711,47 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "in FR1.2 there is another formula for STd.Dev. we can use that also"
+ "### Explanation\n",
+ "##### Explanation 1 \n",
+ "Normal data structure is as shown \n",
+ "\n",
+ "['A','B','C'],\n",
+ "\n",
+ "['1','2','3'],\n",
+ "\n",
+ "['4','5','6'],so on..\n",
+ "\n",
+ "Therfore EachClmToList[0] = ['A','1','4'..]\n",
+ "\n",
+ "##### Explanation 2\n",
+ "For loop is created to reach out to every single data inside 'AppendTolist' in the range of the data length,\n",
+ "(768) or (767) if we count from 0. To be able to do so, 2 for loop should be created as shown, one to count the number of\n",
+ "columns which is (9) or 8 if we count the zero, and the other to count the number of data in each row.\n",
+ "therefore it will start from [0][0].. [1][0].. [2][0] until it reaches [767][0] and switch to [0][1]..\n",
+ "and continue until it reaches the last data in the file which is at [767][8].\n",
+ "while so, the data (numbers) will be appended to a new list called 'EachClmToList'\n",
+ "\n",
+ "##### Explanation 3\n",
+ "A mathematical operation to create a sublist of (each data under each line for the header ) to achieve exploration 1, therefore\n",
+ "for every end of a line create a new list for the next line, and at the end, we will have a total of 9 lists that \n",
+ "achieved to carry each column of data into one list \n",
+ "\n",
+ "\n",
+ "#### From task 1.1 to 1.7\n",
+ "\n",
+ "Overall the qustions can be solved using mathmatical quations using pre-build function in python\n",
+ "\n",
+ "#### For task 1.9 and along\n",
+ "\n",
+ "\n",
+ "\n",
+ "### Strength \n",
+ "### Weaknesses\n",
+ "### Improvement Points \n",
+ "### Alternative\n",
+ "\n"
]
},
- {
- "cell_type": "raw",
- "metadata": {},
- "source": []
- },
{
"cell_type": "markdown",
"metadata": {},