diff --git a/UFCFVQ-15-M Programming Task 2.ipynb b/UFCFVQ-15-M Programming Task 2.ipynb
index cbb343ba7f709b4b0370562fda29d8a36cadb53a..1b10b946fb46d4e623fef6972abf9f671cd4e72c 100644
--- a/UFCFVQ-15-M Programming Task 2.ipynb
+++ b/UFCFVQ-15-M Programming Task 2.ipynb
@@ -632,63 +632,49 @@
"metadata": {},
"outputs": [
{
- "data": {
- "text/plain": [
- "Unnamed: 0 0\n",
- "id_student 0\n",
- "gender 0\n",
- "region 0\n",
- "highest_education 0\n",
- "age_band 0\n",
- "disability 0\n",
- "final_result 0\n",
- "score 19\n",
- "click_events 1371\n",
- "dtype: int64"
- ]
- },
- "execution_count": 4,
- "metadata": {},
- "output_type": "execute_result"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Before Dropping\n",
+ "\n",
+ "Unnamed: 0 0\n",
+ "id_student 0\n",
+ "gender 0\n",
+ "region 0\n",
+ "highest_education 0\n",
+ "age_band 0\n",
+ "disability 0\n",
+ "final_result 0\n",
+ "score 19\n",
+ "click_events 1371\n",
+ "dtype: int64\n",
+ "\n",
+ "After Dropping\n",
+ "\n",
+ "Unnamed: 0 0\n",
+ "id_student 0\n",
+ "gender 0\n",
+ "region 0\n",
+ "highest_education 0\n",
+ "age_band 0\n",
+ "disability 0\n",
+ "final_result 0\n",
+ "score 0\n",
+ "click_events 0\n",
+ "dtype: int64\n",
+ "\n",
+ "The Dataset Shape is (25332, 10)\n"
+ ]
}
],
"source": [
"#Visiling how many null values are there before dropping it\n",
- "Datasetframe.isnull().sum()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Unnamed: 0 0\n",
- "id_student 0\n",
- "gender 0\n",
- "region 0\n",
- "highest_education 0\n",
- "age_band 0\n",
- "disability 0\n",
- "final_result 0\n",
- "score 0\n",
- "click_events 0\n",
- "dtype: int64"
- ]
- },
- "execution_count": 5,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
+ "print(f'Before Dropping\\n\\n{Datasetframe.isnull().sum()}')\n",
"# All rows with empty values will be dropped\n",
"Datasetframe = Datasetframe.dropna()\n",
- "\n",
"#Visiling how many null values are there after dropping it\n",
- "Datasetframe.isnull().sum()"
+ "print(f'\\nAfter Dropping\\n\\n{Datasetframe.isnull().sum()}')\n",
+ "print(f'\\nThe Dataset Shape is {Datasetframe.shape}')"
]
},
{
@@ -700,7 +686,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -882,7 +868,7 @@
" </tr>\n",
" </tbody>\n",
"</table>\n",
- "<p>25259 rows × 10 columns</p>\n",
+ "<p>25254 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
@@ -925,10 +911,10 @@
"26719 275.0 \n",
"26720 616.0 \n",
"\n",
- "[25259 rows x 10 columns]"
+ "[25254 rows x 10 columns]"
]
},
- "execution_count": 6,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -936,7 +922,7 @@
"source": [
"#All click_events under 10 will be removed from the Datasetframes\n",
"\n",
- "Datasetframe = Datasetframe.drop(Datasetframe[Datasetframe['click_events'] < 10].index)\n",
+ "Datasetframe = Datasetframe.drop(Datasetframe[Datasetframe['click_events'] <= 10].index)\n",
"# Outputing the Dataset\n",
"Datasetframe"
]
@@ -950,11 +936,246 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 6,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Unnamed: 0</th>\n",
+ " <th>id_student</th>\n",
+ " <th>gender</th>\n",
+ " <th>region</th>\n",
+ " <th>highest_education</th>\n",
+ " <th>age_band</th>\n",
+ " <th>disability</th>\n",
+ " <th>final_result</th>\n",
+ " <th>final_mark</th>\n",
+ " <th>click_events</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>11391</td>\n",
+ " <td>M</td>\n",
+ " <td>East Anglian Region</td>\n",
+ " <td>HE Qualification</td>\n",
+ " <td>55<=</td>\n",
+ " <td>N</td>\n",
+ " <td>Pass</td>\n",
+ " <td>82.0</td>\n",
+ " <td>934.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>28400</td>\n",
+ " <td>F</td>\n",
+ " <td>Scotland</td>\n",
+ " <td>HE Qualification</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Pass</td>\n",
+ " <td>67.0</td>\n",
+ " <td>1435.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>31604</td>\n",
+ " <td>F</td>\n",
+ " <td>South East Region</td>\n",
+ " <td>A Level or Equivalent</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Pass</td>\n",
+ " <td>76.0</td>\n",
+ " <td>2158.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>32885</td>\n",
+ " <td>F</td>\n",
+ " <td>West Midlands Region</td>\n",
+ " <td>Lower Than A Level</td>\n",
+ " <td>0-35</td>\n",
+ " <td>N</td>\n",
+ " <td>Pass</td>\n",
+ " <td>55.0</td>\n",
+ " <td>1034.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>38053</td>\n",
+ " <td>M</td>\n",
+ " <td>Wales</td>\n",
+ " <td>A Level or Equivalent</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Pass</td>\n",
+ " <td>68.0</td>\n",
+ " <td>2445.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26716</th>\n",
+ " <td>26741</td>\n",
+ " <td>2620947</td>\n",
+ " <td>F</td>\n",
+ " <td>Scotland</td>\n",
+ " <td>A Level or Equivalent</td>\n",
+ " <td>0-35</td>\n",
+ " <td>Y</td>\n",
+ " <td>Distinction</td>\n",
+ " <td>89.0</td>\n",
+ " <td>476.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26717</th>\n",
+ " <td>26742</td>\n",
+ " <td>2645731</td>\n",
+ " <td>F</td>\n",
+ " <td>East Anglian Region</td>\n",
+ " <td>Lower Than A Level</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Distinction</td>\n",
+ " <td>89.0</td>\n",
+ " <td>893.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26718</th>\n",
+ " <td>26743</td>\n",
+ " <td>2648187</td>\n",
+ " <td>F</td>\n",
+ " <td>South Region</td>\n",
+ " <td>A Level or Equivalent</td>\n",
+ " <td>0-35</td>\n",
+ " <td>Y</td>\n",
+ " <td>Pass</td>\n",
+ " <td>77.0</td>\n",
+ " <td>312.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26719</th>\n",
+ " <td>26744</td>\n",
+ " <td>2679821</td>\n",
+ " <td>F</td>\n",
+ " <td>South East Region</td>\n",
+ " <td>Lower Than A Level</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Withdrawn</td>\n",
+ " <td>92.0</td>\n",
+ " <td>275.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26720</th>\n",
+ " <td>26745</td>\n",
+ " <td>2684003</td>\n",
+ " <td>F</td>\n",
+ " <td>Yorkshire Region</td>\n",
+ " <td>HE Qualification</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>Distinction</td>\n",
+ " <td>83.0</td>\n",
+ " <td>616.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>25254 rows × 10 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Unnamed: 0 id_student gender region \\\n",
+ "0 0 11391 M East Anglian Region \n",
+ "1 1 28400 F Scotland \n",
+ "2 2 31604 F South East Region \n",
+ "3 3 32885 F West Midlands Region \n",
+ "4 4 38053 M Wales \n",
+ "... ... ... ... ... \n",
+ "26716 26741 2620947 F Scotland \n",
+ "26717 26742 2645731 F East Anglian Region \n",
+ "26718 26743 2648187 F South Region \n",
+ "26719 26744 2679821 F South East Region \n",
+ "26720 26745 2684003 F Yorkshire Region \n",
+ "\n",
+ " highest_education age_band disability final_result final_mark \\\n",
+ "0 HE Qualification 55<= N Pass 82.0 \n",
+ "1 HE Qualification 35-55 N Pass 67.0 \n",
+ "2 A Level or Equivalent 35-55 N Pass 76.0 \n",
+ "3 Lower Than A Level 0-35 N Pass 55.0 \n",
+ "4 A Level or Equivalent 35-55 N Pass 68.0 \n",
+ "... ... ... ... ... ... \n",
+ "26716 A Level or Equivalent 0-35 Y Distinction 89.0 \n",
+ "26717 Lower Than A Level 35-55 N Distinction 89.0 \n",
+ "26718 A Level or Equivalent 0-35 Y Pass 77.0 \n",
+ "26719 Lower Than A Level 35-55 N Withdrawn 92.0 \n",
+ "26720 HE Qualification 35-55 N Distinction 83.0 \n",
+ "\n",
+ " click_events \n",
+ "0 934.0 \n",
+ "1 1435.0 \n",
+ "2 2158.0 \n",
+ "3 1034.0 \n",
+ "4 2445.0 \n",
+ "... ... \n",
+ "26716 476.0 \n",
+ "26717 893.0 \n",
+ "26718 312.0 \n",
+ "26719 275.0 \n",
+ "26720 616.0 \n",
+ "\n",
+ "[25254 rows x 10 columns]"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# add code here"
+ "# Using panadas rename function to rename 'score' column in Datasetframe to 'final_mark'\n",
+ "\n",
+ "Datasetframe = Datasetframe.rename(columns={'score': 'final_mark'})\n",
+ "\n",
+ "# Outputing the Result\n",
+ "Datasetframe"
]
},
{
@@ -966,11 +1187,199 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 7,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Unnamed: 0</th>\n",
+ " <th>id_student</th>\n",
+ " <th>gender</th>\n",
+ " <th>age_band</th>\n",
+ " <th>disability</th>\n",
+ " <th>final_mark</th>\n",
+ " <th>click_events</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>0</td>\n",
+ " <td>11391</td>\n",
+ " <td>M</td>\n",
+ " <td>55<=</td>\n",
+ " <td>N</td>\n",
+ " <td>82.0</td>\n",
+ " <td>934.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1</td>\n",
+ " <td>28400</td>\n",
+ " <td>F</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>67.0</td>\n",
+ " <td>1435.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2</td>\n",
+ " <td>31604</td>\n",
+ " <td>F</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>76.0</td>\n",
+ " <td>2158.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>3</td>\n",
+ " <td>32885</td>\n",
+ " <td>F</td>\n",
+ " <td>0-35</td>\n",
+ " <td>N</td>\n",
+ " <td>55.0</td>\n",
+ " <td>1034.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>4</td>\n",
+ " <td>38053</td>\n",
+ " <td>M</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>68.0</td>\n",
+ " <td>2445.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26716</th>\n",
+ " <td>26741</td>\n",
+ " <td>2620947</td>\n",
+ " <td>F</td>\n",
+ " <td>0-35</td>\n",
+ " <td>Y</td>\n",
+ " <td>89.0</td>\n",
+ " <td>476.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26717</th>\n",
+ " <td>26742</td>\n",
+ " <td>2645731</td>\n",
+ " <td>F</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>89.0</td>\n",
+ " <td>893.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26718</th>\n",
+ " <td>26743</td>\n",
+ " <td>2648187</td>\n",
+ " <td>F</td>\n",
+ " <td>0-35</td>\n",
+ " <td>Y</td>\n",
+ " <td>77.0</td>\n",
+ " <td>312.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26719</th>\n",
+ " <td>26744</td>\n",
+ " <td>2679821</td>\n",
+ " <td>F</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>92.0</td>\n",
+ " <td>275.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26720</th>\n",
+ " <td>26745</td>\n",
+ " <td>2684003</td>\n",
+ " <td>F</td>\n",
+ " <td>35-55</td>\n",
+ " <td>N</td>\n",
+ " <td>83.0</td>\n",
+ " <td>616.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>25254 rows × 7 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " Unnamed: 0 id_student gender age_band disability final_mark \\\n",
+ "0 0 11391 M 55<= N 82.0 \n",
+ "1 1 28400 F 35-55 N 67.0 \n",
+ "2 2 31604 F 35-55 N 76.0 \n",
+ "3 3 32885 F 0-35 N 55.0 \n",
+ "4 4 38053 M 35-55 N 68.0 \n",
+ "... ... ... ... ... ... ... \n",
+ "26716 26741 2620947 F 0-35 Y 89.0 \n",
+ "26717 26742 2645731 F 35-55 N 89.0 \n",
+ "26718 26743 2648187 F 0-35 Y 77.0 \n",
+ "26719 26744 2679821 F 35-55 N 92.0 \n",
+ "26720 26745 2684003 F 35-55 N 83.0 \n",
+ "\n",
+ " click_events \n",
+ "0 934.0 \n",
+ "1 1435.0 \n",
+ "2 2158.0 \n",
+ "3 1034.0 \n",
+ "4 2445.0 \n",
+ "... ... \n",
+ "26716 476.0 \n",
+ "26717 893.0 \n",
+ "26718 312.0 \n",
+ "26719 275.0 \n",
+ "26720 616.0 \n",
+ "\n",
+ "[25254 rows x 7 columns]"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "# add code here"
+ "# Using panadas drop function to drop the columns ['region', 'final_result','highest education']\n",
+ "# As default the axis is 0, therefore it has been set in here to 1\n",
+ "# Moreover axis 1 will check on all the COLUMNS in each ROW\n",
+ "\n",
+ "Datasetframe = Datasetframe.drop(['region', 'final_result', 'highest_education'], axis=1)\n",
+ "\n",
+ "# printing the output without the dropped columns\n",
+ "Datasetframe"
]
},
{
@@ -982,7 +1391,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
@@ -998,7 +1407,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
@@ -1014,7 +1423,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
@@ -1030,7 +1439,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
@@ -1046,7 +1455,7 @@
},
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 12,
"metadata": {},
"outputs": [],
"source": [