Update...

Update f22/andy_lec_notes/lec12_Oct03_IterationAlgorithms/lec12_Oct03_IterationAlgorithms_completed.ipynb

Update...
b2e05118 · Andy Kuemmel · f08c4664 · b2e05118
Commit b2e05118 authored 2 years ago by Andy Kuemmel
--- a/f22/andy_lec_notes/lec12_Oct03_IterationAlgorithms/lec12_Oct03_IterationAlgorithms_completed.ipynb
+++ b/f22/andy_lec_notes/lec12_Oct03_IterationAlgorithms/lec12_Oct03_IterationAlgorithms_completed.ipynb
@@ -114,7 +114,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
   "id": "d67a080f",
   "metadata": {},
   "outputs": [
@@ -124,7 +124,7 @@
       "992"
      ]
     },
-     "execution_count": 4,
+     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -143,7 +143,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
   "id": "bde8dc35",
   "metadata": {},
   "outputs": [
@@ -153,7 +153,7 @@
       "'21'"
      ]
     },
-     "execution_count": 5,
+     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -165,7 +165,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
   "id": "b0f87a2c",
   "metadata": {},
   "outputs": [
@@ -175,7 +175,7 @@
       "str"
      ]
     },
-     "execution_count": 6,
+     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -197,7 +197,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
   "id": "ba993090",
   "metadata": {},
   "outputs": [
@@ -207,7 +207,7 @@
       "'LEC001'"
      ]
     },
-     "execution_count": 7,
+     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -218,7 +218,7 @@
  },
  {
   "cell_type": "markdown",
-   "id": "6e3e3c0a",
+   "id": "d6edf4d5",
   "metadata": {},
   "source": [
    "### What are the age and pizza choices of the first 10 students? \n",
@@ -227,8 +227,8 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 7,
-   "id": "46ec7632",
+   "id": "883e25cc",
   "metadata": {},
   "outputs": [
    {
@@ -264,7 +264,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 8,
   "id": "e024c488",
   "metadata": {},
   "outputs": [
@@ -296,7 +296,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
   "id": "38bd778a",
   "metadata": {},
   "outputs": [
@@ -336,7 +336,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 10,
   "id": "ea77e0cd",
   "metadata": {},
   "outputs": [
@@ -351,7 +351,7 @@
   "source": [
    "min_age = int(project.get_age(0) )  #assume first student is youngest,and has age\n",
    "for i in range(project.count()):\n",
-    "    if project.get_lecture != \"LEC001\":\n",
+    "    if project.get_lecture(i) != \"LEC001\":\n",
    "        continue\n",
    "    if project.get_age(i) == '': \n",
    "        continue\n",
@@ -363,6 +363,36 @@
    "print(min_age)"
   ]
  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "c6b48319",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "17\n"
+     ]
+    }
+   ],
+   "source": [
+    "# REDO this using None as an initial value for min_age\n",
+    "min_age = None\n",
+    "for i in range(project.count()):\n",
+    "    if project.get_lecture(i) != \"LEC001\":\n",
+    "        continue\n",
+    "    if project.get_age(i) == '': \n",
+    "        continue\n",
+    "    age = int(project.get_age(i))\n",
+    "    if age < 0 or age > 100:\n",
+    "        continue\n",
+    "    if min_age == None or age < min_age:\n",
+    "        min_age = age\n",
+    "print(min_age)"
+   ]
+  },
  {
   "cell_type": "markdown",
   "id": "296c2a49",
@@ -373,7 +403,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 11,
   "id": "8b7c8367",
   "metadata": {},
   "outputs": [
@@ -383,7 +413,7 @@
       "19.608180839612487"
      ]
     },
-     "execution_count": 38,
+     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
@@ -415,24 +445,48 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 16,
   "id": "a524873b",
   "metadata": {},
   "outputs": [
    {
-     "data": {
+     "name": "stdout",
-      "text/plain": [
+     "output_type": "stream",
-       "17"
+     "text": [
-      ]
+      "17 Statistics\n"
-     },
+     ]
-     "execution_count": 36,
-     "metadata": {},
-     "output_type": "execute_result"
    }
   ],
   "source": [
    "# we will do this in lecture on Wednesday\n",
-    "    "
+    "# use None\n",
+    "# keep track of two variables, the min_age and index of the min_age\n",
+    "\n",
+    "    \n",
+    "min_age = None\n",
+    "min_age_idx = None\n",
+    "for i in range(project.count()):\n",
+    "    if project.get_lecture(i) != \"LEC001\":\n",
+    "        continue\n",
+    "    if project.get_age(i) == '': \n",
+    "        continue\n",
+    "    age = int(project.get_age(i))\n",
+    "    if age < 0 or age > 100:\n",
+    "        continue\n",
+    "    if min_age == None or age < min_age:\n",
+    "        min_age = age\n",
+    "        min_age_idx = i\n",
+    "print(min_age, project.get_major(min_age_idx))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "84adf236",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# help(project)"
   ]
  },
  {
@@ -445,7 +499,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 21,
   "id": "fada2a40",
   "metadata": {},
   "outputs": [
@@ -453,22 +507,27 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "19 <class 'str'>\n"
+      "None\n"
     ]
    }
   ],
   "source": [
+    "# REDO THIS USING NONE\n",
+    "\n",
+    "target_zip = 53715\n",
+    "target_lecture = \"LEC001\"\n",
+    "age_of_target = None\n",
    "for i in range(project.count()):\n",
-    "    # put a print statement here\n",
+    "    if project.get_lecture(i) == target_lecture and project.get_zip_code(i) == target_zip:\n",
-    "    if project.get_lecture(i) == \"LEC002\" and project.get_zip_code(i) == \"53715\":\n",
+    "        age_of_target = project.get_age(i)\n",
-    "        print(project.get_age(i), type(project.get_age(i)))\n",
+    "        break # often in a search we break to be efficient\n",
-    "        break"
+    "print(age_of_target)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
-   "id": "772f7a58",
+   "id": "7a3fdbf6",
   "metadata": {},
   "outputs": [
    {

 %% Cell type:markdown id:6a76ef95 tags:
 # Iteration Algorithms
 Thanks to CS 220 campus students for their data and to Meena for putting together the project.py file
 %% Cell type:markdown id:103da70b tags:
 ## Learning Objectives
 - Iterate through a dataset using for idx in range(project.count())
 - Compute the frequency of data that meets a certain criteria
 - Find the maximum or minimum value of a numeric column in a dataset
    - Handle missing numeric values when computing a maximum / minimum
    - Use the index of a maximum or minimum to access other information about that data item
 - Use break and continue in for loops when processing a dataset
 %% Cell type:code id:28961628 tags:
 ``` python
 import project
 ```
 %% Cell type:code id:d1dca7ae tags:
 ``` python
 # TODO: inspect the project module's documentation by using help
 help(project)
 ```
 %% Output
    Help on module project:
    NAME
        project
    FUNCTIONS
        __init__()
        count()
            This function will return the number of records in the dataset
        get_age(idx)
            get_age(idx) returns the age of the student in row idx
        get_latitude(idx)
            get_latitude(idx) returns the latitude of the student's favourite place in row idx
        get_lecture(idx)
            get_lecture(idx) returns the lecture of the student in row idx
        get_longitude(idx)
            get_longitude(idx) returns the longitude of the student's favourite place in row idx
        get_major(idx)
            get_major(idx) returns the major of the student in row idx
        get_pet_owner(idx)
            get_pet_owner(idx) returns the pet preference of student in row idx
        get_piazza_topping(idx)
            get_piazza_topping(idx) returns the preferred pizza toppings of the student in row idx
        get_procrastinator(idx)
            get_procrastinator(idx) returns whether student in row idx is a procrastinator
        get_runner(idx)
            get_runner(idx) returns whether student in row idx is a runner
        get_sleep_habit(idx)
            get_sleep_habit(idx) returns the sleep habit of the student in row idx
        get_zip_code(idx)
            get_zip_code(idx) returns the residential zip code of the student in row idx
    DATA
        __student__ = [{'Age': '22', 'Latitude': '43.073051', 'Lecture': 'LEC0...
    FILE
        /Users/andrewkuemmel/cs220-f22/lectures/lec12_Oct03_IterationAlgorithms/project.py
 %% Cell type:markdown id:7fb78f6b tags:
 ### How many students does the dataset have?
 %% Cell type:code id:d67a080f tags:
 ``` python
 project.count()
 ```
 %% Output
    992
 %% Cell type:markdown id:3c97d494 tags:
 ### What is the age of the student at index 10?
 %% Cell type:code id:bde8dc35 tags:
 ``` python
 id_10_age = project.get_age(10)
 id_10_age
 ```
 %% Output
    '21'
 %% Cell type:code id:b0f87a2c tags:
 ``` python
 # TODO: what is the return value type of the get_age function?
 type(id_10_age)
 # in a CSV file, all data stored as a string
 ```
 %% Output
    str
 %% Cell type:markdown id:37898141 tags:
 ### What is the lecture number of the student at index 20?
 %% Cell type:code id:ba993090 tags:
 ``` python
 project.get_lecture(20)
 ```
 %% Output
    'LEC001'
-%% Cell type:markdown id:6e3e3c0a tags:
+%% Cell type:markdown id:d6edf4d5 tags:
 ### What are the age and pizza choices of the first 10 students?
-%% Cell type:code id:46ec7632 tags:
+%% Cell type:code id:883e25cc tags:
 ``` python
 for i in range(10):
    print(project.get_age(i), project.get_piazza_topping(i))
 ```
 %% Output
    22 none (just cheese)
     none (just cheese)
    18 none (just cheese)
     none (just cheese)
     none (just cheese)
    18 none (just cheese)
     none (just cheese)
    18 pineapple
    18 none (just cheese)
    18 pepperoni
 %% Cell type:markdown id:af3d9d8c tags:
 ### How many current lecture (example: LEC001) students are in the dataset?
 %% Cell type:code id:e024c488 tags:
 ``` python
 frequency = 0
 for i in range(project.count()):
    if project.get_lecture(i) == "LEC001":
        frequency += 1
 print(frequency)
 ```
 %% Output
    195
 %% Cell type:markdown id:b9ff6434 tags:
 ### What is the age of the oldest student in the course?
 %% Cell type:code id:38bd778a tags:
 ``` python
 # find the maximum
 # check for missing data
 # check for data out of range
 max_age = 0
 for i in range(project.count()):
    if project.get_age(i) == '':
        continue
    age = int(project.get_age(i))
    if age < 0 or age > 100:
        continue
    if age > max_age:
        max_age = age
 print(max_age)
 ```
 %% Output
    53
 %% Cell type:markdown id:b40a32fb tags:
 ### What is the age of the youngest student in current lecture (example: LEC001)?
 - use similar algorithm as above question
 %% Cell type:code id:ea77e0cd tags:
 ``` python
 min_age = int(project.get_age(0) )  #assume first student is youngest,and has age
 for i in range(project.count()):
-    if project.get_lecture != "LEC001":
+    if project.get_lecture(i) != "LEC001":
        continue
    if project.get_age(i) == '':
        continue
    age = int(project.get_age(i))
    if age < 0 or age > 100:
        continue
    if age < min_age:
        min_age = age
 print(min_age)
 ```
 %% Output
    22
+%% Cell type:code id:c6b48319 tags:
+``` python
+# REDO this using None as an initial value for min_age
+min_age = None
+for i in range(project.count()):
+    if project.get_lecture(i) != "LEC001":
+        continue
+    if project.get_age(i) == '':
+        continue
+    age = int(project.get_age(i))
+    if age < 0 or age > 100:
+        continue
+    if min_age == None or age < min_age:
+        min_age = age
+print(min_age)
+```
+%% Output
+    17
 %% Cell type:markdown id:296c2a49 tags:
 ### What is the average age of students enrolled in CS220 / CS319?
 %% Cell type:code id:8b7c8367 tags:
 ``` python
 total_age = 0
 num_students_with_age = 0
 for i in range(project.count()):
    if project.get_age(i) == '':
        continue
    age = int(project.get_age(i))
    if age < 0 or age > 100:
        continue
    total_age += age
    num_students_with_age += 1
 average_age = total_age / num_students_with_age
 average_age
 ```
 %% Output
    19.608180839612487
 %% Cell type:markdown id:48f1c791 tags:
 ### What major is the youngest student in current lecture (example: LEC001) planning to declare?
 - now, we need to find some other detail about the youngest student
 - often, you'll have to keep track of ID of the max or min, so that you can retrive other details about that data entry
 %% Cell type:code id:a524873b tags:
 ``` python
 # we will do this in lecture on Wednesday
+# use None
+# keep track of two variables, the min_age and index of the min_age
+min_age = None
+min_age_idx = None
+for i in range(project.count()):
+    if project.get_lecture(i) != "LEC001":
+        continue
+    if project.get_age(i) == '':
+        continue
+    age = int(project.get_age(i))
+    if age < 0 or age > 100:
+        continue
+    if min_age == None or age < min_age:
+        min_age = age
+        min_age_idx = i
+print(min_age, project.get_major(min_age_idx))
 ```
 %% Output
-    17
+    17 Statistics
+%% Cell type:code id:84adf236 tags:
+``` python
+# help(project)
+```
 %% Cell type:markdown id:5294702a tags:
 ### Considering current lecture students (example: LEC001), what is the age of the first student residing at zip code 53715?
 %% Cell type:code id:fada2a40 tags:
 ``` python
+# REDO THIS USING NONE
+target_zip = 53715
+target_lecture = "LEC001"
+age_of_target = None
 for i in range(project.count()):
-    # put a print statement here
+    if project.get_lecture(i) == target_lecture and project.get_zip_code(i) == target_zip:
-    if project.get_lecture(i) == "LEC002" and project.get_zip_code(i) == "53715":
+        age_of_target = project.get_age(i)
-        print(project.get_age(i), type(project.get_age(i)))
+        break # often in a search we break to be efficient
-        break
+print(age_of_target)
 ```
 %% Output
-    19 <class 'str'>
+    None
-%% Cell type:code id:772f7a58 tags:
+%% Cell type:code id:7a3fdbf6 tags:
 ``` python
 help(project)
 ```
 %% Output
    Help on module project:
    NAME
        project
    FUNCTIONS
        __init__()
        count()
            This function will return the number of records in the dataset
        get_age(idx)
            get_age(idx) returns the age of the student in row idx
        get_latitude(idx)
            get_latitude(idx) returns the latitude of the student's favourite place in row idx
        get_lecture(idx)
            get_lecture(idx) returns the lecture of the student in row idx
        get_longitude(idx)
            get_longitude(idx) returns the longitude of the student's favourite place in row idx
        get_major(idx)
            get_major(idx) returns the major of the student in row idx
        get_pet_owner(idx)
            get_pet_owner(idx) returns the pet preference of student in row idx
        get_piazza_topping(idx)
            get_piazza_topping(idx) returns the preferred pizza toppings of the student in row idx
        get_procrastinator(idx)
            get_procrastinator(idx) returns whether student in row idx is a procrastinator
        get_runner(idx)
            get_runner(idx) returns whether student in row idx is a runner
        get_sleep_habit(idx)
            get_sleep_habit(idx) returns the sleep habit of the student in row idx
        get_zip_code(idx)
            get_zip_code(idx) returns the residential zip code of the student in row idx
    DATA
        __student__ = [{'Age': '22', 'Latitude': '43.073051', 'Lecture': 'LEC0...
    FILE
        /Users/andrewkuemmel/cs220-f22/lectures/lec12_Oct03_IterationAlgorithms/project.py
 %% Cell type:markdown id:68793d99 tags:
 ## Self-practice
 %% Cell type:markdown id:2eeed867 tags:
 ### How many current lecture (example: LEC001) students are runners?
 %% Cell type:markdown id:1ea57e12 tags:
 ### How many current lecture (example: LEC001) students are procrastinators?
 %% Cell type:markdown id:cf0ac7c8 tags:
 ### How many current lecture (example: LEC001) students own or have owned a pet?
 %% Cell type:markdown id:ffd5e10f tags:
 ### What sleep habit does the youngest student in current lecture (example: LEC001) have?
 - try to solve this from scratch, instead of copy-pasting code to find mimimum age
 %% Cell type:markdown id:f255b95a tags:
 ### What sleep habit does the oldest student in current lecture (example: LEC001) have?
 - try to solve this from scratch, instead of copy-pasting code to find mimimum age
 %% Cell type:markdown id:70a8ac57 tags:
 ### What is the minimum latitude (& corresponding longitude) of a student's place of interest?
 - What place is this -> try to enter the lat, long on Google maps?
 %% Cell type:markdown id:581ea197 tags:
 ### What is the maximum latitude (& corresponding longitude) of a student's place of interest?
 - What place is this -> try to enter the lat, long on Google maps?
 %% Cell type:code id:fcee0994 tags:
 ``` python
 ```