diff --git a/lecture_material/05-oop1/in_class_demo_lec2.ipynb b/lecture_material/05-oop1/in_class_demo_lec2.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..53f96f226f206c006c04c483fd94a9b13c5979ad
--- /dev/null
+++ b/lecture_material/05-oop1/in_class_demo_lec2.ipynb
@@ -0,0 +1,1224 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "3ad30ce8-1eca-4633-bc69-9ccbe0180e8e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "52e6c912-27c8-4aa2-a3c7-780cc70299a6",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/tmp/ipykernel_16573/3756477020.py:1: DtypeWarning: Columns (22,23,24,26,27,28,29,30,31,32,33,38,43,44) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+ " df = pd.read_csv(\"wi.csv\")\n"
+ ]
+ }
+ ],
+ "source": [
+ "df = pd.read_csv(\"wi.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "b069d5d4-4e22-4321-a1db-e47e4d46afd9",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df1 = df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "4d6fd21d-fa12-4eac-a58b-e92344e492ee",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df = 123"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "7ccc7e53-cae0-46af-88e5-77ffffc6195b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "df1 = None"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "05a3e388-839a-497d-ac60-e1478f802d70",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/tmp/ipykernel_16573/3756477020.py:1: DtypeWarning: Columns (22,23,24,26,27,28,29,30,31,32,33,38,43,44) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+ " df = pd.read_csv(\"wi.csv\")\n"
+ ]
+ }
+ ],
+ "source": [
+ "df = pd.read_csv(\"wi.csv\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "65431158-8919-402c-8dcd-d850ff2f1891",
+ "metadata": {},
+ "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>activity_year</th>\n",
+ " <th>lei</th>\n",
+ " <th>derived_msa-md</th>\n",
+ " <th>state_code</th>\n",
+ " <th>county_code</th>\n",
+ " <th>census_tract</th>\n",
+ " <th>conforming_loan_limit</th>\n",
+ " <th>derived_loan_product_type</th>\n",
+ " <th>derived_dwelling_category</th>\n",
+ " <th>derived_ethnicity</th>\n",
+ " <th>...</th>\n",
+ " <th>denial_reason-2</th>\n",
+ " <th>denial_reason-3</th>\n",
+ " <th>denial_reason-4</th>\n",
+ " <th>tract_population</th>\n",
+ " <th>tract_minority_population_percent</th>\n",
+ " <th>ffiec_msa_md_median_family_income</th>\n",
+ " <th>tract_to_msa_income_percentage</th>\n",
+ " <th>tract_owner_occupied_units</th>\n",
+ " <th>tract_one_to_four_family_homes</th>\n",
+ " <th>tract_median_age_of_housing_units</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>2020</td>\n",
+ " <td>549300FX7K8PTEQUU487</td>\n",
+ " <td>31540</td>\n",
+ " <td>WI</td>\n",
+ " <td>55025.0</td>\n",
+ " <td>5.502500e+10</td>\n",
+ " <td>C</td>\n",
+ " <td>Conventional:First Lien</td>\n",
+ " <td>Single Family (1-4 Units):Site-Built</td>\n",
+ " <td>Not Hispanic or Latino</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3572</td>\n",
+ " <td>41.15</td>\n",
+ " <td>96600</td>\n",
+ " <td>64</td>\n",
+ " <td>812</td>\n",
+ " <td>910</td>\n",
+ " <td>45</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2020</td>\n",
+ " <td>549300FX7K8PTEQUU487</td>\n",
+ " <td>99999</td>\n",
+ " <td>WI</td>\n",
+ " <td>55013.0</td>\n",
+ " <td>5.501397e+10</td>\n",
+ " <td>C</td>\n",
+ " <td>Conventional:First Lien</td>\n",
+ " <td>Single Family (1-4 Units):Site-Built</td>\n",
+ " <td>Not Hispanic or Latino</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2333</td>\n",
+ " <td>9.90</td>\n",
+ " <td>68000</td>\n",
+ " <td>87</td>\n",
+ " <td>1000</td>\n",
+ " <td>2717</td>\n",
+ " <td>34</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2 rows × 99 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " activity_year lei derived_msa-md state_code \\\n",
+ "0 2020 549300FX7K8PTEQUU487 31540 WI \n",
+ "1 2020 549300FX7K8PTEQUU487 99999 WI \n",
+ "\n",
+ " county_code census_tract conforming_loan_limit derived_loan_product_type \\\n",
+ "0 55025.0 5.502500e+10 C Conventional:First Lien \n",
+ "1 55013.0 5.501397e+10 C Conventional:First Lien \n",
+ "\n",
+ " derived_dwelling_category derived_ethnicity ... \\\n",
+ "0 Single Family (1-4 Units):Site-Built Not Hispanic or Latino ... \n",
+ "1 Single Family (1-4 Units):Site-Built Not Hispanic or Latino ... \n",
+ "\n",
+ " denial_reason-2 denial_reason-3 denial_reason-4 tract_population \\\n",
+ "0 NaN NaN NaN 3572 \n",
+ "1 NaN NaN NaN 2333 \n",
+ "\n",
+ " tract_minority_population_percent ffiec_msa_md_median_family_income \\\n",
+ "0 41.15 96600 \n",
+ "1 9.90 68000 \n",
+ "\n",
+ " tract_to_msa_income_percentage tract_owner_occupied_units \\\n",
+ "0 64 812 \n",
+ "1 87 1000 \n",
+ "\n",
+ " tract_one_to_four_family_homes tract_median_age_of_housing_units \n",
+ "0 910 45 \n",
+ "1 2717 34 \n",
+ "\n",
+ "[2 rows x 99 columns]"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.head(2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "d5190089-62f8-4c82-a125-e5d761f5c1a6",
+ "metadata": {},
+ "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>activity_year</th>\n",
+ " <th>lei</th>\n",
+ " <th>derived_msa-md</th>\n",
+ " <th>state_code</th>\n",
+ " <th>county_code</th>\n",
+ " <th>census_tract</th>\n",
+ " <th>conforming_loan_limit</th>\n",
+ " <th>derived_loan_product_type</th>\n",
+ " <th>derived_dwelling_category</th>\n",
+ " <th>derived_ethnicity</th>\n",
+ " <th>...</th>\n",
+ " <th>denial_reason-2</th>\n",
+ " <th>denial_reason-3</th>\n",
+ " <th>denial_reason-4</th>\n",
+ " <th>tract_population</th>\n",
+ " <th>tract_minority_population_percent</th>\n",
+ " <th>ffiec_msa_md_median_family_income</th>\n",
+ " <th>tract_to_msa_income_percentage</th>\n",
+ " <th>tract_owner_occupied_units</th>\n",
+ " <th>tract_one_to_four_family_homes</th>\n",
+ " <th>tract_median_age_of_housing_units</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>468269</th>\n",
+ " <td>2020</td>\n",
+ " <td>549300FX7K8PTEQUU487</td>\n",
+ " <td>36780</td>\n",
+ " <td>WI</td>\n",
+ " <td>55139.0</td>\n",
+ " <td>5.513900e+10</td>\n",
+ " <td>C</td>\n",
+ " <td>Conventional:Subordinate Lien</td>\n",
+ " <td>Single Family (1-4 Units):Site-Built</td>\n",
+ " <td>Not Hispanic or Latino</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4886</td>\n",
+ " <td>15.04</td>\n",
+ " <td>80800</td>\n",
+ " <td>102</td>\n",
+ " <td>1099</td>\n",
+ " <td>1563</td>\n",
+ " <td>36</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>468270</th>\n",
+ " <td>2020</td>\n",
+ " <td>549300FX7K8PTEQUU487</td>\n",
+ " <td>33340</td>\n",
+ " <td>WI</td>\n",
+ " <td>55079.0</td>\n",
+ " <td>5.507902e+10</td>\n",
+ " <td>C</td>\n",
+ " <td>Conventional:First Lien</td>\n",
+ " <td>Single Family (1-4 Units):Site-Built</td>\n",
+ " <td>Hispanic or Latino</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6961</td>\n",
+ " <td>28.13</td>\n",
+ " <td>83800</td>\n",
+ " <td>93</td>\n",
+ " <td>1732</td>\n",
+ " <td>2138</td>\n",
+ " <td>50</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>468271</th>\n",
+ " <td>2020</td>\n",
+ " <td>549300FX7K8PTEQUU487</td>\n",
+ " <td>33460</td>\n",
+ " <td>WI</td>\n",
+ " <td>55109.0</td>\n",
+ " <td>5.510912e+10</td>\n",
+ " <td>C</td>\n",
+ " <td>Conventional:Subordinate Lien</td>\n",
+ " <td>Single Family (1-4 Units):Site-Built</td>\n",
+ " <td>Hispanic or Latino</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>9057</td>\n",
+ " <td>6.41</td>\n",
+ " <td>97300</td>\n",
+ " <td>100</td>\n",
+ " <td>2448</td>\n",
+ " <td>3368</td>\n",
+ " <td>17</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>3 rows × 99 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " activity_year lei derived_msa-md state_code \\\n",
+ "468269 2020 549300FX7K8PTEQUU487 36780 WI \n",
+ "468270 2020 549300FX7K8PTEQUU487 33340 WI \n",
+ "468271 2020 549300FX7K8PTEQUU487 33460 WI \n",
+ "\n",
+ " county_code census_tract conforming_loan_limit \\\n",
+ "468269 55139.0 5.513900e+10 C \n",
+ "468270 55079.0 5.507902e+10 C \n",
+ "468271 55109.0 5.510912e+10 C \n",
+ "\n",
+ " derived_loan_product_type derived_dwelling_category \\\n",
+ "468269 Conventional:Subordinate Lien Single Family (1-4 Units):Site-Built \n",
+ "468270 Conventional:First Lien Single Family (1-4 Units):Site-Built \n",
+ "468271 Conventional:Subordinate Lien Single Family (1-4 Units):Site-Built \n",
+ "\n",
+ " derived_ethnicity ... denial_reason-2 denial_reason-3 \\\n",
+ "468269 Not Hispanic or Latino ... NaN NaN \n",
+ "468270 Hispanic or Latino ... NaN NaN \n",
+ "468271 Hispanic or Latino ... NaN NaN \n",
+ "\n",
+ " denial_reason-4 tract_population tract_minority_population_percent \\\n",
+ "468269 NaN 4886 15.04 \n",
+ "468270 NaN 6961 28.13 \n",
+ "468271 NaN 9057 6.41 \n",
+ "\n",
+ " ffiec_msa_md_median_family_income tract_to_msa_income_percentage \\\n",
+ "468269 80800 102 \n",
+ "468270 83800 93 \n",
+ "468271 97300 100 \n",
+ "\n",
+ " tract_owner_occupied_units tract_one_to_four_family_homes \\\n",
+ "468269 1099 1563 \n",
+ "468270 1732 2138 \n",
+ "468271 2448 3368 \n",
+ "\n",
+ " tract_median_age_of_housing_units \n",
+ "468269 36 \n",
+ "468270 50 \n",
+ "468271 17 \n",
+ "\n",
+ "[3 rows x 99 columns]"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.tail(3)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "850faeeb-116f-4c56-aa61-05bcde7719fa",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['activity_year', 'lei', 'derived_msa-md', 'state_code', 'county_code',\n",
+ " 'census_tract', 'conforming_loan_limit', 'derived_loan_product_type',\n",
+ " 'derived_dwelling_category', 'derived_ethnicity', 'derived_race',\n",
+ " 'derived_sex', 'action_taken', 'purchaser_type', 'preapproval',\n",
+ " 'loan_type', 'loan_purpose', 'lien_status', 'reverse_mortgage',\n",
+ " 'open-end_line_of_credit', 'business_or_commercial_purpose',\n",
+ " 'loan_amount', 'loan_to_value_ratio', 'interest_rate', 'rate_spread',\n",
+ " 'hoepa_status', 'total_loan_costs', 'total_points_and_fees',\n",
+ " 'origination_charges', 'discount_points', 'lender_credits', 'loan_term',\n",
+ " 'prepayment_penalty_term', 'intro_rate_period', 'negative_amortization',\n",
+ " 'interest_only_payment', 'balloon_payment',\n",
+ " 'other_nonamortizing_features', 'property_value', 'construction_method',\n",
+ " 'occupancy_type', 'manufactured_home_secured_property_type',\n",
+ " 'manufactured_home_land_property_interest', 'total_units',\n",
+ " 'multifamily_affordable_units', 'income', 'debt_to_income_ratio',\n",
+ " 'applicant_credit_score_type', 'co-applicant_credit_score_type',\n",
+ " 'applicant_ethnicity-1', 'applicant_ethnicity-2',\n",
+ " 'applicant_ethnicity-3', 'applicant_ethnicity-4',\n",
+ " 'applicant_ethnicity-5', 'co-applicant_ethnicity-1',\n",
+ " 'co-applicant_ethnicity-2', 'co-applicant_ethnicity-3',\n",
+ " 'co-applicant_ethnicity-4', 'co-applicant_ethnicity-5',\n",
+ " 'applicant_ethnicity_observed', 'co-applicant_ethnicity_observed',\n",
+ " 'applicant_race-1', 'applicant_race-2', 'applicant_race-3',\n",
+ " 'applicant_race-4', 'applicant_race-5', 'co-applicant_race-1',\n",
+ " 'co-applicant_race-2', 'co-applicant_race-3', 'co-applicant_race-4',\n",
+ " 'co-applicant_race-5', 'applicant_race_observed',\n",
+ " 'co-applicant_race_observed', 'applicant_sex', 'co-applicant_sex',\n",
+ " 'applicant_sex_observed', 'co-applicant_sex_observed', 'applicant_age',\n",
+ " 'co-applicant_age', 'applicant_age_above_62',\n",
+ " 'co-applicant_age_above_62', 'submission_of_application',\n",
+ " 'initially_payable_to_institution', 'aus-1', 'aus-2', 'aus-3', 'aus-4',\n",
+ " 'aus-5', 'denial_reason-1', 'denial_reason-2', 'denial_reason-3',\n",
+ " 'denial_reason-4', 'tract_population',\n",
+ " 'tract_minority_population_percent',\n",
+ " 'ffiec_msa_md_median_family_income', 'tract_to_msa_income_percentage',\n",
+ " 'tract_owner_occupied_units', 'tract_one_to_four_family_homes',\n",
+ " 'tract_median_age_of_housing_units'],\n",
+ " dtype='object')"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.columns"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "ceec5d46-ff31-462b-a0cb-94f62f67e4cc",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 NaN\n",
+ "1 3.0\n",
+ "2 NaN\n",
+ "3 3.75\n",
+ "4 2.5\n",
+ " ... \n",
+ "468267 2.25\n",
+ "468268 2.5\n",
+ "468269 4.25\n",
+ "468270 NaN\n",
+ "468271 NaN\n",
+ "Name: interest_rate, Length: 468272, dtype: object"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[\"interest_rate\"]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "26c1afa9-79cd-4096-a490-f9080f3fe02b",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "interest_rate\n",
+ "Exempt 37959\n",
+ "3.0 22584\n",
+ "2.75 22480\n",
+ "3.25 21343\n",
+ "2.875 21201\n",
+ " ... \n",
+ "3.023 1\n",
+ "2.632 1\n",
+ "3.345 1\n",
+ "3.364 1\n",
+ "2.32 1\n",
+ "Name: count, Length: 2080, dtype: int64"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df[\"interest_rate\"].value_counts()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "a0af4324-50a1-4ae3-87a6-6eba608ff1cd",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "ValueError",
+ "evalue": "Unable to parse string \"Exempt\" at position 1505",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
+ "File \u001b[0;32mlib.pyx:2368\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[0;34m()\u001b[0m\n",
+ "\u001b[0;31mValueError\u001b[0m: Unable to parse string \"Exempt\"",
+ "\nDuring handling of the above exception, another exception occurred:\n",
+ "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[15], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mpd\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto_numeric\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43minterest_rate\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n",
+ "File \u001b[0;32m~/.local/lib/python3.10/site-packages/pandas/core/tools/numeric.py:222\u001b[0m, in \u001b[0;36mto_numeric\u001b[0;34m(arg, errors, downcast, dtype_backend)\u001b[0m\n\u001b[1;32m 220\u001b[0m coerce_numeric \u001b[38;5;241m=\u001b[39m errors \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m (\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m 221\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 222\u001b[0m values, new_mask \u001b[38;5;241m=\u001b[39m \u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmaybe_convert_numeric\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# type: ignore[call-overload] # noqa: E501\u001b[39;49;00m\n\u001b[1;32m 223\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalues\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 224\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mset\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 225\u001b[0m \u001b[43m \u001b[49m\u001b[43mcoerce_numeric\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcoerce_numeric\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 226\u001b[0m \u001b[43m \u001b[49m\u001b[43mconvert_to_masked_nullable\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype_backend\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mnot\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mno_default\u001b[49m\n\u001b[1;32m 227\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43misinstance\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mvalues_dtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mStringDtype\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 228\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 229\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mValueError\u001b[39;00m, \u001b[38;5;167;01mTypeError\u001b[39;00m):\n\u001b[1;32m 230\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m errors \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mraise\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n",
+ "File \u001b[0;32mlib.pyx:2410\u001b[0m, in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[0;34m()\u001b[0m\n",
+ "\u001b[0;31mValueError\u001b[0m: Unable to parse string \"Exempt\" at position 1505"
+ ]
+ }
+ ],
+ "source": [
+ "pd.to_numeric(df[\"interest_rate\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "5be93ff0-c7c8-438a-b140-6dfa9624a067",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 NaN\n",
+ "1 3.00\n",
+ "2 NaN\n",
+ "3 3.75\n",
+ "4 2.50\n",
+ " ... \n",
+ "468267 2.25\n",
+ "468268 2.50\n",
+ "468269 4.25\n",
+ "468270 NaN\n",
+ "468271 NaN\n",
+ "Name: interest_rate, Length: 468272, dtype: float64"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.to_numeric(df[\"interest_rate\"], errors= \"coerce\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "689dc2c0-c051-49b8-aee2-ac8e6b5a575f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3.266264315063852"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.to_numeric(df[\"interest_rate\"], errors= \"coerce\").dropna().mean()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "c11270c9-9a44-480c-8564-16c314940c4e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/tmp/ipykernel_16573/264512408.py:2: DtypeWarning: Columns (22,23,24,26,27,28,29,30,31,32,33,38,43,44) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+ " pd.read_csv(f)\n"
+ ]
+ }
+ ],
+ "source": [
+ "f = open(\"wi.csv\")\n",
+ "pd.read_csv(f)\n",
+ "f.close()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9c04585e-8ab8-4138-b229-b4119a6a06d6",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "open(..., mode = \"r\")--> text\n",
+ "open(..., mode = \"rb\")--> bytes\n",
+ "zf.open(..., mode = \"r\")--> bytes always"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "2df5c81c-7fdf-47da-b581-dd15c0abed8c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3.266264315063054"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import zipfile\n",
+ "import csv\n",
+ "from io import TextIOWrapper\n",
+ "\n",
+ "zf = zipfile.ZipFile(\"wi.zip\")\n",
+ "\n",
+ "f = zf.open(\"wi.csv\")\n",
+ "\n",
+ "total = 0\n",
+ "count = 0\n",
+ "\n",
+ "reader = csv.DictReader(TextIOWrapper(f))\n",
+ "for row in reader:\n",
+ " try:\n",
+ " total += float(row[\"interest_rate\"])\n",
+ " count += 1\n",
+ " except ValueError:\n",
+ " pass # do nothing\n",
+ "\n",
+ "f.close()\n",
+ "zf.close()\n",
+ "\n",
+ "total/count"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "e97422c0-8ed9-4e20-8104-432dd1bea109",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3.266264315063054"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "def get_rates_v1():\n",
+ " rates = []\n",
+ " zf = zipfile.ZipFile(\"wi.zip\")\n",
+ "\n",
+ " f = zf.open(\"wi.csv\")\n",
+ "\n",
+ "\n",
+ " reader = csv.DictReader(TextIOWrapper(f))\n",
+ " for row in reader:\n",
+ " try:\n",
+ " rates.append(float(row[\"interest_rate\"]))\n",
+ "\n",
+ " except ValueError:\n",
+ " pass # do nothing\n",
+ "\n",
+ " f.close()\n",
+ " zf.close()\n",
+ " return rates\n",
+ "\n",
+ "rates = get_rates_v1()\n",
+ "\n",
+ "sum(rates)/len(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "739424b6-cf67-4821-b626-23fcd500f8ce",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<generator object get_rates_v2 at 0x7f1da61c6c00>"
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "def get_rates_v2():\n",
+ " \n",
+ " print(\"Test\")\n",
+ " zf = zipfile.ZipFile(\"wi.zip\")\n",
+ "\n",
+ " f = zf.open(\"wi.csv\")\n",
+ "\n",
+ "\n",
+ " reader = csv.DictReader(TextIOWrapper(f))\n",
+ " for row in reader:\n",
+ " try:\n",
+ " yield float(row[\"interest_rate\"])\n",
+ "\n",
+ " except ValueError:\n",
+ " pass # do nothing\n",
+ "\n",
+ " f.close()\n",
+ " zf.close()\n",
+ "\n",
+ "get_rates_v2()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "02f60cb5-77a8-475b-a7e9-6815b74b9637",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "3.0"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rates = get_rates_v2()\n",
+ "next(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "id": "d64cf45a-f878-4b5c-98f0-d906a1ff0456",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "3.75"
+ ]
+ },
+ "execution_count": 19,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "next(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 20,
+ "id": "a6fbcec3-cbce-4e6c-8579-7b344d49ab05",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2.5"
+ ]
+ },
+ "execution_count": 20,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "next(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "0d99bdf7-c367-4cad-9306-ffb0aba20bca",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2.75"
+ ]
+ },
+ "execution_count": 21,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "next(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "8ee28948-1a2f-431b-988b-d11f626f5844",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "object of type 'generator' has no len()",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[22], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mrates\u001b[49m\u001b[43m)\u001b[49m\n",
+ "\u001b[0;31mTypeError\u001b[0m: object of type 'generator' has no len()"
+ ]
+ }
+ ],
+ "source": [
+ "len(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 23,
+ "id": "5a9eac32-d40f-4bf4-881b-3442488a3ff8",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "'generator' object is not subscriptable",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[23], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mrates\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\n",
+ "\u001b[0;31mTypeError\u001b[0m: 'generator' object is not subscriptable"
+ ]
+ }
+ ],
+ "source": [
+ "rates[0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 24,
+ "id": "4cf8a3e1-6705-4762-8982-19ce6c1072cf",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "3.266264315063054"
+ ]
+ },
+ "execution_count": 24,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "rates = get_rates_v2()\n",
+ "total = 0\n",
+ "count = 0\n",
+ "\n",
+ "for rate in rates:\n",
+ " total += rate\n",
+ " count += 1\n",
+ "total/count"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 25,
+ "id": "c6da348e-7975-4306-a338-e536325b6394",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test\n"
+ ]
+ }
+ ],
+ "source": [
+ "rates = get_rates_v2()\n",
+ "\n",
+ "L = list(rates)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "id": "0e0f6133-08b2-4210-8ea4-ddf16e20ad6e",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "324658"
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(L)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "id": "9ce88f36-f50a-4e61-94dd-348922d1add8",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# L"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "f14e7d46-94d7-424f-95d1-f6c9ff4bef70",
+ "metadata": {},
+ "source": [
+ "# OOP 1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "id": "65f96fc3-46a6-4e01-b1de-20b701c5727e",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Dog:\n",
+ " pass\n",
+ "\n",
+ " def speak(d):\n",
+ " if d.age < 3:\n",
+ " print(f\"{d.name} barks: woof!woof!woof!\")\n",
+ " else:\n",
+ " print(f\"{d.name} barks: woof!\")\n",
+ "\n",
+ "def init(dog, name, how_old):\n",
+ " dog.name = name\n",
+ " dog.age = how_old\n",
+ " \n",
+ " \n",
+ "dog1 = Dog()\n",
+ "# # type(dog1)\n",
+ "# dog1.name = \"Fido\"\n",
+ "# dog1.age = 2\n",
+ "\n",
+ "init(dog1, \"Fido\", 2)\n",
+ "\n",
+ "dog2= Dog()\n",
+ "# dog2.name = \"Sam\"\n",
+ "# dog2.age = 5\n",
+ "init(dog2, \"Sam\", 5)\n",
+ "\n",
+ "# speak(dog1)\n",
+ "# speak(dog2)\n",
+ "pets = [dog1, dog2]\n",
+ "\n",
+ "# for pet in pets:\n",
+ "# speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "id": "c8d2fe89-8b97-416a-a273-62ff0a0131b7",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Cat:\n",
+ " pass\n",
+ "\n",
+ " def speak(cat):\n",
+ " print(\"meow\")\n",
+ "\n",
+ "cat = Cat()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 46,
+ "id": "9fade852-7da2-433a-8d35-ec12831d98dd",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "meow\n",
+ "meow\n",
+ "meow\n"
+ ]
+ }
+ ],
+ "source": [
+ "pets = [dog1, dog2, cat]\n",
+ "\n",
+ "for pet in pets:\n",
+ " Cat.speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 48,
+ "id": "439fdc25-112d-4156-9559-fe08faa54f2a",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 48,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "type(dog1) == Dog"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 49,
+ "id": "7fdf917e-ea86-4652-9926-0dd412539e96",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fido barks: woof!woof!woof!\n",
+ "Sam barks: woof!\n",
+ "meow\n"
+ ]
+ }
+ ],
+ "source": [
+ "#bad version\n",
+ "\n",
+ "for pet in pets:\n",
+ " if type(pet) == Dog:\n",
+ " Dog.speak(pet)\n",
+ " elif type(pet) == Cat:\n",
+ " Cat.speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 51,
+ "id": "f585fdce-03ca-43ef-828b-29b661dcaac9",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fido barks: woof!woof!woof!\n",
+ "Sam barks: woof!\n",
+ "meow\n"
+ ]
+ }
+ ],
+ "source": [
+ "#better version\n",
+ "\n",
+ "for pet in pets:\n",
+ " type(pet).speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 53,
+ "id": "2f833df0-be23-4d4f-b5be-56b66f6b4150",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Fido barks: woof!woof!woof!\n",
+ "Sam barks: woof!\n",
+ "meow\n"
+ ]
+ }
+ ],
+ "source": [
+ "#best version\n",
+ "for pet in pets:\n",
+ " pet.speak() #type(pet).speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 54,
+ "id": "d8c37f76-ad91-4487-8832-1eef17d8c545",
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "TypeError",
+ "evalue": "Dog.speak() takes 1 positional argument but 2 were given",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
+ "Cell \u001b[0;32mIn[54], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m pet \u001b[38;5;129;01min\u001b[39;00m pets:\n\u001b[0;32m----> 2\u001b[0m \u001b[43mpet\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mspeak\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHi\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m#type(pet).speak(pet)\u001b[39;00m\n",
+ "\u001b[0;31mTypeError\u001b[0m: Dog.speak() takes 1 positional argument but 2 were given"
+ ]
+ }
+ ],
+ "source": [
+ "for pet in pets:\n",
+ " pet.speak(\"Hi\") #type(pet).speak(pet)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "60bab56c-1f4c-4923-9173-044be5c36ed1",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.10.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}