diff --git a/UFCFVQ-15-M Programming Task 1.ipynb b/UFCFVQ-15-M Programming Task 1.ipynb
index 217f4c6f34319cb61b681598192e410ed62b0d3d..7709324229324a10a6ff7dba8355f4a0b5729f26 100644
--- a/UFCFVQ-15-M Programming Task 1.ipynb
+++ b/UFCFVQ-15-M Programming Task 1.ipynb
@@ -70,7 +70,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "The mean of the list = 120.895\n"
+ "The mean of the list = 120.89453125\n"
]
}
],
@@ -79,33 +79,15 @@
"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",
" global ListMean\n",
- " MeanListSum = 0\n",
- " MeanListLength = 0\n",
- " \n",
- " #Find the sum of the list using pure python\n",
- " for DataInList in List:\n",
- " MeanListSum += DataInList\n",
- " \n",
- " #Find the Length of the list using pure python \n",
- " for DataLength in List:\n",
- " MeanListLength += 1\n",
" \n",
" #Find the mean of the list using the mathematical mean equation\n",
- " ListMean = MeanListSum/MeanListLength\n",
- " \n",
- " #Print The result and round it to 3 decimal places \n",
- " print(f'The mean of the list = {round(ListMean,3)}')\n",
- "\n",
- " ###\n",
- " ##Fast Alternative way with pre-built python functions\n",
- " ##---\n",
- " #meanEq = sum(List)/len(List)\n",
- " #return meanEq\n",
- " ##---\n",
- " ###\n",
+ " ListMean = sum(List)/len(List)\n",
" \n",
+ " #Rturn The result\n",
+ " return ListMean\n",
+ "\n",
"#Calling the function and passing the >> List << argument to it \n",
- "meanFinder(List)"
+ "print(f'The mean of the list = {meanFinder(List)}')"
]
},
{
@@ -132,37 +114,24 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Standard Devision of the list = 31.952\n"
+ "Standard Devision of the list = 31.95179590820272\n"
]
}
],
"source": [
"#Function to find the standard deviation\n",
- "def StdDevFinder(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",
- " global STD_DEV\n",
- " \n",
- " \n",
- " #Find the sum of the list using pre-bulid python function (len)\n",
- " StdListSum = sum(List)\n",
- " \n",
- " #Find the length of the list using pre-bulid python function (len)\n",
- " StdListLength = len(List)\n",
- " \n",
- " #Find the mean of the list\n",
- " StdListMean = StdListSum/StdListLength\n",
- " \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",
- " StdVariance = sum((DataInList - StdListMean)**2 for DataInList in List) / StdListLength\n",
+ " StdVariance = sum((DataInList - ListMean)**2 for DataInList in List) / len(List)\n",
" STD_DEV = StdVariance ** 0.5\n",
" \n",
- " #Print The result and round it to 3 decimal places \n",
- " print(f'Standard Devision of the list = {round(STD_DEV,3)}')\n",
+ " #Rturn The result\n",
+ " return STD_DEV\n",
"\n",
"\n",
"#Calling the function and passing the >> List << argument to it \n",
- "StdDevFinder(List)"
+ "print(f'Standard Devision of the list = {StdDevFinder(List)}')"
]
},
{
@@ -190,55 +159,27 @@
"output_type": "stream",
"text": [
"The minimum number in the list = 0\n",
- "The max number in the list = 199\n"
+ "The maximum in the list = 199\n"
]
}
],
"source": [
"#Function to find the minimum value in a python list\n",
"def MinFinder(List):\n",
- " #set a variable that carry the first number in the list to compare it with other numbers in the list\n",
- " ListMin=List[0]\n",
- " #For loop to accsses each number in the list\n",
- " for numbers in range(1,len(List)):\n",
- " #If the new number is smaller than the next number in the list, assign it as (ListMin) 'the new smallest number'\n",
- " if List[numbers] <ListMin:\n",
- " ListMin=List[numbers] \n",
- " #Print out the smallest number \n",
- " print(f'The minimum number in the list = {ListMin}')\n",
- " \n",
- " ###\n",
- " ##Fast Alternative way with pre-built python functions\n",
- " ##---\n",
- " #ListMin = min(List)\n",
- " #return ListMin\n",
- " ##---\n",
- " ###\n",
+ " ListMin = min(List)\n",
+ " return ListMin\n",
+ "\n",
"\n",
"#Function to find the maximum value in a python list\n",
"def MaxFinder(List):\n",
- " #set a variable that carry the first number in the list to compare it with other numbers in the list\n",
- " ListMax=List[0]\n",
- " #For loop to accsses each number in the list\n",
- " for numbers in range(1,len(List)):\n",
- " #If the new number is bigger than the next number in the list, assign it as (ListMax) 'the new largest number'\n",
- " if(List[numbers]>ListMax):\n",
- " ListMax=List[numbers]\n",
- " #Print out the largest number \n",
- " print(f'The max number in the list = {ListMax}')\n",
- " \n",
- " ###\n",
- " ##Fast Alternative way with pre-build python functions\n",
- " ##---\n",
- " #ListMax = max(List)\n",
- " #return ListMax\n",
- " ##---\n",
- " ###\n",
- " \n",
+ " ListMax = max(List)\n",
+ " return ListMax\n",
+ "\n",
" \n",
"#Calling the functions and passing the >> List << argument to it \n",
- "MinFinder(List)\n",
- "MaxFinder(List)"
+ "print(f'The minimum number in the list = {MinFinder(List)}')\n",
+ "\n",
+ "print(f'The maximum in the list = {MaxFinder(List)}')\n"
]
},
{
@@ -419,7 +360,7 @@
"TabularDic = {\n",
" 'Count':len(List),\n",
" 'Mean':round(ListMean,3),\n",
- " 'StdDev':round(STD_DEV,3),\n",
+ " 'StdDev':round(StdDevFinder(List),3),\n",
" 'Minimum':min(List),\n",
" '25 percentile':percentileOf_25,\n",
" '50 percentile':percentileOf_50,\n",
@@ -457,7 +398,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "[+] Memory Size >>> 3.638 (KB) | 3638 Bytes | 0.003638 (MB)\n",
+ "[+] 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",
@@ -480,14 +421,14 @@
"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 in memory\n",
- " print(f'[+] Memory Size >>> {FileSize*0.001} (KB) | {FileSize} Bytes | {round(FileSize*0.000001,6)} (MB)\\n')\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}\")\n"
+ "print(f\"[+] The file content as shown:\\n\\n{List[0:]}\")\n"
]
},
{
@@ -505,12 +446,87 @@
"### Requirement FR1.9 - Design and build a data structure to store CSV data in memory"
]
},
+ {
+ "cell_type": "markdown",
+ "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 "
+ ]
+ },
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 11,
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "CsvFile = open('task1.csv','r')\n",
+ "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",
+ "EachClmToList = [] #Creating an empty list to append Each column-row (each data under each line for the header ) \n",
+ "\n",
+ "'''\n",
+ "For loop to read the data inside the CSV file and remove all (\\n). therefore all data will be on the same line\n",
+ "but split by a (,) so each line is a sublist, eg. [[Row 1],[Row 2],[Row 3]..]\n",
+ "'''\n",
+ "for data in CsvFile: \n",
+ " data = data.replace('\\n','').split(',')\n",
+ " 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 subList in AppendTolist[0]: \n",
+ " ColumnHeader.append(subList) #append to another list. \n",
+ "#Removing the appended it from the main list 'AppendTolist'\n",
+ "AppendTolist.remove(AppendTolist[0])\n",
+ "\n",
+ "#Refer to Explanation (2) \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",
+ " 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",
+ "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"
+ ]
},
{
"cell_type": "markdown",
@@ -529,10 +545,34 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 12,
"metadata": {},
- "outputs": [],
- "source": []
+ "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"
+ ]
+ }
+ ],
+ "source": [
+ "#Creating function to construct the data structure and to call it after. \n",
+ "def dataStrcuture():\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()"
+ ]
},
{
"cell_type": "markdown",
@@ -551,16 +591,63 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 91,
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\"Stats\" : [\"Mean\",\"Stdev\", \"Min\", Max\",\"25%\",\"50%\",\"75%\"]\n",
+ "\n",
+ "\"Pregnancies\" : [3.845, 3.367, 0.0, 17.0, 1.0, 3.0, 6.0]\n",
+ "\"Glucose\" : [120.895, 31.952, 0.0, 199.0, 99.0, 117.0, 141.0]\n",
+ "\"BloodPressure\" : [69.105, 19.343, 0.0, 122.0, 62.0, 72.0, 80.0]\n",
+ "\"SkinThickness\" : [20.536, 15.942, 0.0, 99.0, 0.0, 23.0, 32.0]\n",
+ "\"Insulin\" : [79.799, 115.169, 0.0, 846.0, 0.0, 32.0, 128.0]\n",
+ "\"BMI\" : [31.993, 7.879, 0.0, 67.1, 27.3, 32.0, 36.6]\n",
+ "\"DiabetesPedigreeFunction\" : [0.472, 0.331, 0.078, 2.42, 0.244, 0.374, 0.627]\n",
+ "\"Age\" : [33.241, 11.753, 21.0, 81.0, 24.0, 29.0, 41.0]\n",
+ "\"Outcome\" : [0.349, 0.477, 0.0, 1.0, 0.0, 0.0, 1.0]\n"
+ ]
+ }
+ ],
+ "source": [
+ "print('\"Stats\" : [\"Mean\",\"Stdev\", \"Min\", Max\",\"25%\",\"50%\",\"75%\"]\\n')\n",
+ "#Calling the file \n",
+ "def dataStrcuture():\n",
+ " global data\n",
+ " #Creating an empty list to append Each column-row (each data under each line for the header ) \n",
+ " ConvertdeToFloat = []\n",
+ "\n",
+ " #For loop to convet rto float in a way that it can be called later in other tasks.\n",
+ " 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",
+ " for x in range(len(ColumnHeader)):\n",
+ " data = [round(meanFinder(ConvertdeToFloat[x][:]),3),\n",
+ " round(StdDevFinder((ConvertdeToFloat[x][:])),3),\n",
+ " MinFinder(ConvertdeToFloat[x][:]),\n",
+ " MaxFinder(ConvertdeToFloat[x][:]),\n",
+ " percentileFinder(ConvertdeToFloat[x][:],25), \n",
+ " percentileFinder(ConvertdeToFloat[x][:],50),\n",
+ " percentileFinder(ConvertdeToFloat[x][:],75)\n",
+ " ]\n",
+ " print(f'\"{ColumnHeader[x]}\" : {data}')\n",
+ " \n",
+ "dataStrcuture()"
+ ]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "##### MARK: %\n",
+ "# MARK: %\n",
"#### FEEDBACK: "
]
},
@@ -573,10 +660,75 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 94,
"metadata": {},
- "outputs": [],
- "source": []
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "*************************************************************************************************************************\n",
+ " Status Mean Stdev Min Max 25% 50% 75% \n",
+ "*************************************************************************************************************************\n",
+ " Pregnancies 3.845 3.367 17.0 0.0 1.0 3.0 6.0\n",
+ " Glucose 120.895 31.952 199.0 0.0 99.0 117.0 141.0\n",
+ " BloodPressure 69.105 19.343 122.0 0.0 62.0 72.0 80.0\n",
+ " SkinThickness 20.536 15.942 99.0 0.0 0.0 23.0 32.0\n",
+ " Insulin 79.799 115.169 846.0 0.0 0.0 32.0 128.0\n",
+ " BMI 31.993 7.879 67.1 0.0 27.3 32.0 36.6\n",
+ " DiabPedFnc 0.472 0.331 2.42 0.078 0.244 0.374 0.627\n",
+ " Age 33.241 11.753 81.0 21.0 24.0 29.0 41.0\n",
+ " Outcome 0.349 0.477 1.0 0.0 0.0 0.0 1.0\n",
+ "*************************************************************************************************************************\n"
+ ]
+ }
+ ],
+ "source": [
+ "#Calling the file \n",
+ "def dataStrcuture():\n",
+ " \n",
+ " newList = [element.replace('DiabetesPedigreeFunction', 'DiabPedFnc') for element in ColumnHeader]\n",
+ " clmName = [newList]\n",
+ " Status = [\"Mean\",\"Stdev\", \"Min\", \"Max\",\"25%\",\"50%\",\"75%\"]\n",
+ " format_row = \"{: >13} \" * (len(Status)+1)\n",
+ " print(stars.rjust(121,'*'))\n",
+ " print(format_row.format(\"Status\", *Status))\n",
+ " print(stars.rjust(121,'*'))\n",
+ "\n",
+ " ConvertdeToFloat = []\n",
+ " \n",
+ " #For loop to convet into float in a way that it can be called later in other tasks.\n",
+ " Status = [\"Mean\",\"Stdev\", \"Min\", \"Max\",\"25%\",\"50%\",\"75%\"]\n",
+ "\n",
+ " for x in range(len(ColumnHeader)): \n",
+ " EachClmInListToFloat = list(map(float,EachClmToList[x][:]))\n",
+ " ConvertdeToFloat.append(EachClmInListToFloat)\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",
+ " for x in range(len(ColumnHeader)):\n",
+ "\n",
+ " data = [[round(meanFinder(ConvertdeToFloat[x][:]),3),\n",
+ " round(StdDevFinder((ConvertdeToFloat[x][:])),3),\n",
+ " MaxFinder(ConvertdeToFloat[x][:]),\n",
+ " MinFinder(ConvertdeToFloat[x][:]),\n",
+ " percentileFinder(ConvertdeToFloat[x][:],25), \n",
+ " percentileFinder(ConvertdeToFloat[x][:],50),\n",
+ " percentileFinder(ConvertdeToFloat[x][:],75)\n",
+ " ]]\n",
+ "\n",
+ " format_row = \"{:>15}\" * (len(Status) + 1)\n",
+ " \n",
+ " for names, row in zip(clmName, data):\n",
+ " #print(team[x])\n",
+ " print(format_row.format(names[x], *row))\n",
+ "\n",
+ "\n",
+ "dataStrcuture()\n",
+ "stars = '*'\n",
+ "print(stars.rjust(121,'*'))"
+ ]
},
{
"cell_type": "markdown",