########>>  INTITIALIZE  <<########
#basic operation libraries
import os
import sys
import ast
import datetime
import re
import time

#data analysis libraries
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

#mathematical libraries
import math

#geospacial libraries
from geopy.geocoders import Nominatim
from geopy.distance import geodesic

#display settings for Jupyter display, feel free to edit
from IPython.display import display, HTML

#display settings for Pandas, feel free to edit
pd.set_option('display.html.table_schema', True)
pd.set_option('expand_frame_repr', True)
pd.set_option('display.max_colwidth', 200)
pd.options.display.html.use_mathjax = False

#manage warnings
import warnings
warnings.filterwarnings('ignore')

# using the following script allows me to 'know' when my block of code has completed
print ("\n" + '{:<5} : {:2}'.format("Finished", str(datetime.datetime.now())))

Finished : 2025-10-09 21:20:08.314505

apt = pd.read_csv(r"C:\Users\alexp\Downloads\Charlotte Apartments.csv")

apt

print(apt.dtypes)

Complex          object
Address          object
Unit_Variant     object
Bedrooms         object
Bathrooms       float64
Rent            float64
Sqft            float64
Amenities        object
Website          object
dtype: object

apt['Bedrooms'] = apt['Bedrooms'].replace('Studio', 0)
apt['Bedrooms'] = pd.to_numeric(apt['Bedrooms'], errors='coerce').astype('Int64')

apt

# --------------------------
# 1. Apartment Data Example
# --------------------------
# Extract unique complexes and addresses
unique_apartments = apt[["Complex", "Address"]].drop_duplicates().reset_index(drop=True)

apt_df = pd.DataFrame(unique_apartments)

# Drop rows with NaN values in Complex or Address
apt_df = apt_df.dropna(subset=["Complex", "Address"]).reset_index(drop=True)

apt_df

# --------------------------
# 2. Neighborhood Landmarks
# --------------------------
landmarks_df = pd.DataFrame({
    "Neighborhood": [
        "Uptown", "South End", "NoDa", "SouthPark",
        "University City", "West Charlotte", "South Charlotte"
    ],
    "Landmark": [
        "Bank of America Stadium",
        "Atherton Mill & Market",
        "The Evening Muse",
        "SouthPark Mall",
        "UNC Charlotte Main Campus",
        "Freedom Park",
        "Carowinds Theme Park"
    ],
    "Address": [
        "800 S Mint St, Charlotte, NC 28202",
        "2140 South Blvd, Charlotte, NC 28203",
        "322 E 36th St, Charlotte, NC 28205",
        "4400 Sharon Rd, Charlotte, NC 28211",
        "9201 University City Blvd, Charlotte, NC 28223",
        "1900 East Blvd, Charlotte, NC 28203",
        "14523 Carowinds Blvd, Charlotte, NC 28273"
    ]
})

landmarks_df

# --------------------------
# 3. Initialize geocoder
# --------------------------
geolocator = Nominatim(user_agent="charlotte_geo")

def geocode_address(address):
    try:
        location = geolocator.geocode(address)
        if location:
            return (location.latitude, location.longitude)
        else:
            return (None, None)
    except:
        return (None, None)

# --------------------------
# 4. Geocode landmarks
# --------------------------
landmarks_df["Coordinates"] = landmarks_df["Address"].apply(lambda x: geocode_address(x))
time.sleep(1)  # polite pause

# --------------------------
# 5. Geocode apartments
# --------------------------
apt_df["Coordinates"] = apt_df["Address"].apply(lambda x: geocode_address(x))
time.sleep(1)

# --------------------------
# 6. Assign neighborhood based on closest landmark
# --------------------------
def assign_neighborhood(apartment_coord):
    # If apartment_coord is missing, return None
    if not apartment_coord or None in apartment_coord:
        return None  

    min_distance = float('inf')
    closest_neighborhood = None

    for _, row in landmarks_df.iterrows():
        landmark_coord = row["Coordinates"]

        # Skip only if landmark coordinates are missing
        if not landmark_coord or None in landmark_coord:
            continue  

        distance = geodesic(apartment_coord, landmark_coord).miles

        if distance < min_distance:
            min_distance = distance
            closest_neighborhood = row["Neighborhood"]

    # Always return the closest one found
    return closest_neighborhood

# Apply to dataframe
apt_df["Neighborhood"] = apt_df["Coordinates"].apply(assign_neighborhood)


# --------------------------
# 7. Final DataFrame
# --------------------------
apt_df[["Complex", "Address", "Neighborhood"]]

# Merge neighborhood info from apt_df into the full apt dataframe
apt = apt.merge(
    apt_df[["Complex", "Neighborhood"]],
    on="Complex",
    how="left"
)

# Verify the merge
apt.head()

apt.to_csv("Charlotte_Apartments.csv", index=False)

# Drop fully empty rows
apt = apt.dropna(how='all').reset_index(drop=True)

# Now calculate missing Rent %
missing_rent_pct = apt['Rent'].isna().mean() * 100
print(f"Percentage of missing Rent values: {missing_rent_pct:.2f}%")

Percentage of missing Rent values: 20.00%

apt['Rent'] = apt.groupby(['Complex', 'Bedrooms'])['Rent'].transform(lambda x: x.fillna(x.mean()))

apt['Rent'].isna().mean() * 100

np.float64(0.0)

unit_stats = apt.groupby('Bedrooms').agg(
    Mean_Rent=('Rent', 'mean'),
    Median_Rent=('Rent', 'median'),
    Min_Rent=('Rent', 'min'),
    Max_Rent=('Rent', 'max'),
    Std_Rent=('Rent', 'std'),
    Mean_Sqft=('Sqft', 'mean'),
    Median_Sqft=('Sqft', 'median'),
    Price_per_Sqft=('Rent', lambda x: (x/apt.loc[x.index, 'Sqft']).mean())
).reset_index()

unit_stats = pd.DataFrame(unit_stats)

unit_stats

complex_stats = apt.groupby('Complex').agg(
    Mean_Rent=('Rent', 'mean'),
    Median_Rent=('Rent', 'median'),
    Min_Rent=('Rent', 'min'),
    Max_Rent=('Rent', 'max'),
    Mean_Sqft=('Sqft', 'mean'),
    Amenities_Count=('Amenities', lambda x: x.str.split(';').apply(len).mean())
).reset_index()

complex_stats= pd.DataFrame(complex_stats)

complex_stats

neighborhood_stats = apt.groupby('Neighborhood').agg(
    Mean_Rent=('Rent', 'mean'),
    Median_Rent=('Rent', 'median'),
    Mean_Sqft=('Sqft', 'mean'),
    Units_Count=('Complex', 'count')
).reset_index()

neighborhood_stats = pd.DataFrame(neighborhood_stats)

neighborhood_stats

# Rent range by complex
rent_range_complex = apt.groupby('Complex').agg(
    Min_Rent=('Rent', 'min'),
    Max_Rent=('Rent', 'max')
).reset_index()
rent_range_complex['Rent_Range'] = rent_range_complex['Max_Rent'] - rent_range_complex['Min_Rent']
rent_range_complex

# CV = std / mean
cv_complex = apt.groupby('Complex').agg(
    Mean_Rent=('Rent', 'mean'),
    Std_Rent=('Rent', 'std')
).reset_index()
cv_complex['Rent_CV'] = cv_complex['Std_Rent'] / cv_complex['Mean_Rent']
cv_complex

percentiles_complex = apt.groupby('Complex')['Rent'].quantile([0.25, 0.75]).unstack()
percentiles_complex = percentiles_complex.rename(columns={0.25: '25th_Percentile', 0.75: '75th_Percentile'}).reset_index()
percentiles_complex

# Boxplot by Complex
plt.figure(figsize=(12,6))
sns.boxplot(x='Complex', y='Rent', data=apt)
plt.xticks(rotation=45, ha='right')
plt.title('Rent Distribution by Complex')
plt.show()

# Boxplot by Bedrooms
plt.figure(figsize=(8,6))
sns.boxplot(x='Bedrooms', y='Rent', data=apt)
plt.title('Rent Distribution by Bedrooms')
plt.show()

# Boxplot by Neighborhood
plt.figure(figsize=(10,6))
sns.boxplot(x='Neighborhood', y='Rent', data=apt)
plt.xticks(rotation=45, ha='right')
plt.title('Rent Distribution by Neighborhood')
plt.show()

# Make sure both columns exist
apt['price_per_sqft'] = apt['Rent'] / apt['Sqft']

pps_summary = apt.groupby(['Complex', 'Neighborhood']).agg(
    mean_rent=('Rent', 'mean'),
    mean_sqft=('Sqft', 'mean'),
    mean_ppsf=('price_per_sqft', 'mean'),
    median_ppsf=('price_per_sqft', 'median'),
    count=('Rent', 'size')
).reset_index()

pps_summary

plt.figure(figsize=(10,6))

sns.scatterplot(
    data=pps_summary,
    x="mean_sqft",
    y="mean_rent",
    hue="Neighborhood",
    s=80,
    alpha=0.7
)

# Add regression (trendline) across all complexes
sns.regplot(
    data=pps_summary,
    x="mean_sqft",
    y="mean_rent",
    scatter=False,
    color="black",
    line_kws={"linestyle":"--", "alpha":0.8}
)

plt.xlabel("Mean Square Footage")
plt.ylabel("Mean Rent ($)")
plt.title("Rent vs Square Footage with Trendline")
plt.legend(title="Neighborhood")
plt.grid(True, linestyle="--", alpha=0.5)
plt.show()

plt.figure(figsize=(12,6))
sns.boxplot(data=apt, x='Neighborhood', y='price_per_sqft')
plt.title("Price per Square Foot Distribution by Neighborhood")
plt.show()

# Split the 'Amenities' column into lists
apt['Amenities_List'] = apt['Amenities'].fillna('').apply(lambda x: [a.strip().lower() for a in x.split(';') if a.strip()])

# 1. Total number of amenities per unit
apt['Total_Amenities'] = apt['Amenities_List'].apply(len)

# 2. Proportion of units with certain key amenities (example: pool, gym, parking, pet-friendly)
key_amenities = {
    'pool': ['pool'],
    'gym': ['gym', 'fitness'],
    'parking': ['parking'],
    'pet_friendly': ['pet-friendly', 'pet friendly', 'pet spa']
}

# Create binary columns for each key amenity using substring match
for col_name, keywords in key_amenities.items():
    apt[col_name] = apt['Amenities_List'].apply(lambda x: 1 if any(any(keyword in a for keyword in keywords) for a in x) else 0)

# Aggregate by complex
complex_amenities = apt.groupby('Complex').agg(
    Total_Units=('Unit_Variant', 'count'),
    Mean_Total_Amenities=('Total_Amenities', 'mean'),
    Pool_Proportion=('pool', 'mean'),
    Gym_Proportion=('gym', 'mean'),
    Parking_Proportion=('parking', 'mean'),
    Pet_Friendly_Proportion=('pet_friendly', 'mean')
).reset_index()

# 3. Amenity diversity: count of unique amenities across units in a complex
#complex_amenities['Amenity_Diversity'] = apt.groupby('Complex')['Amenities_List'].apply(
 #   lambda lists: len(set(a for sublist in lists for a in sublist))
#).values

# Display results
complex_amenities

# --- 1. Flag studios ---
apt['Is_Studio'] = apt['Bedrooms'].astype(str).eq('Studio')

# --- 2. Convert numeric bedrooms ---
apt['Bedrooms_Numeric'] = pd.to_numeric(apt['Bedrooms'], errors='coerce')

# --- 3. Replace 0 bedrooms with NaN to avoid division by zero ---
apt.loc[apt['Bedrooms_Numeric'] == 0, 'Bedrooms_Numeric'] = np.nan

# --- 4. Compute Sqft per Bedroom for numeric bedrooms ---
apt['Sqft_per_Bedroom'] = apt['Sqft'] / apt['Bedrooms_Numeric']

# --- 5. Create a separate column for studio sqft ---
apt['Studio_Sqft'] = np.where(apt['Is_Studio'], apt['Sqft'], np.nan)

# --- 6. Separate numeric bedrooms and studios ---
numeric_units = apt[~apt['Bedrooms_Numeric'].isna()]
studio_units = apt[apt['Is_Studio']]

# --- 7. Aggregate numeric bedrooms ---
numeric_stats = numeric_units.groupby(['Complex', 'Bedrooms']).agg(
    Mean_Sqft_per_Bedroom=('Sqft_per_Bedroom', 'mean'),
    Median_Sqft_per_Bedroom=('Sqft_per_Bedroom', 'median'),
    Min_Sqft_per_Bedroom=('Sqft_per_Bedroom', 'min'),
    Max_Sqft_per_Bedroom=('Sqft_per_Bedroom', 'max'),
    Std_Sqft_per_Bedroom=('Sqft_per_Bedroom', 'std')
).reset_index()

# --- 8. Aggregate studios as separate rows ---
studio_stats = studio_units.groupby('Complex').agg(
    Mean_Sqft_per_Bedroom=('Studio_Sqft', 'mean')
).reset_index()
studio_stats['Bedrooms'] = 'Studio'
studio_stats['Median_Sqft_per_Bedroom'] = studio_stats['Mean_Sqft_per_Bedroom']
studio_stats['Min_Sqft_per_Bedroom'] = studio_stats['Mean_Sqft_per_Bedroom']
studio_stats['Max_Sqft_per_Bedroom'] = studio_stats['Mean_Sqft_per_Bedroom']
studio_stats['Std_Sqft_per_Bedroom'] = np.nan

# --- 9. Combine numeric and studio stats ---
unit_size_stats = pd.concat([numeric_stats, studio_stats], ignore_index=True)
unit_size_stats.sort_values(['Complex', 'Bedrooms'], inplace=True)
unit_size_stats.reset_index(drop=True, inplace=True)

unit_size_stats

# --- 3. Histogram of Sqft per Bedroom ---
plt.figure(figsize=(10,6))
sns.histplot(apt['Sqft_per_Bedroom'], bins=30, kde=True, color="steelblue")
plt.title("Distribution of Sqft per Bedroom (All Units)")
plt.xlabel("Sqft per Bedroom")
plt.ylabel("Frequency")
plt.show()

# --- 4. Violin Plot by Complex ---
plt.figure(figsize=(12,6))
sns.violinplot(x="Complex", y="Sqft_per_Bedroom", data=apt, inner="box", cut=0)
plt.xticks(rotation=45, ha="right")
plt.title("Distribution of Sqft per Bedroom by Complex")
plt.xlabel("Complex")
plt.ylabel("Sqft per Bedroom")
plt.show()

# --- 5. Scatter Plot: Rent vs. Sqft per Bedroom ---
plt.figure(figsize=(10,6))
sns.scatterplot(x="Sqft_per_Bedroom", y="Rent", hue="Neighborhood", data=apt, alpha=0.7)
plt.title("Rent vs. Sqft per Bedroom (colored by Neighborhood)")
plt.xlabel("Sqft per Bedroom")
plt.ylabel("Rent")
plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')
plt.show()

# Ensure apt has no duplicate index issues
apt_clean = apt.reset_index(drop=True)

# Compute z-scores for rent within each bedroom type
apt_clean['Rent_Z'] = apt_clean.groupby('Bedrooms')['Rent'].transform(
    lambda x: (x - x.mean()) / x.std()
)

# Flag outliers (commonly |z| > 3)
apt_clean['Outlier_Rent'] = apt_clean['Rent_Z'].abs() > 3

# Show only units flagged as outliers, sorted by z-score
rent_outliers = apt_clean[apt_clean['Outlier_Rent']].sort_values(by='Rent_Z', ascending=False)

# Display key columns for review
rent_outliers = rent_outliers[['Complex', 'Address', 'Unit_Variant', 'Bedrooms', 'Rent', 'Sqft', 'Rent_Z']]

# Output
rent_outliers

# Reset index to make sure 'Bedrooms' is only a column
apt_reset = apt.reset_index(drop=True)

# Function to flag outliers using IQR
def flag_outliers(group):
    Q1 = group['Rent'].quantile(0.25)
    Q3 = group['Rent'].quantile(0.75)
    IQR = Q3 - Q1
    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR
    group['Outlier_Rent'] = (group['Rent'] < lower_bound) | (group['Rent'] > upper_bound)
    return group

# Apply IQR outlier detection per bedroom type
apt_reset = apt_reset.groupby('Bedrooms', group_keys=False).apply(flag_outliers)

# Show only the flagged outliers
rent_outliers = apt_reset[apt_reset['Outlier_Rent']].sort_values(by='Rent', ascending=False)

# Display key columns
rent_outliers[['Complex', 'Address', 'Unit_Variant', 'Bedrooms', 'Rent', 'Sqft', 'Outlier_Rent']]

sns.boxplot(data=apt, x='Bedrooms', y='Rent')
plt.title("Rent Distribution by Bedroom Type")
plt.show()

# --- 1. Create numeric features if not already ---
apt_reset = apt.reset_index(drop=True)

# Count of amenities per unit
apt_reset['Amenities_Count'] = apt_reset['Amenities'].str.count(';') + 1  # assuming ';' separates amenities

# Ensure Bedrooms numeric
apt_reset['Bedrooms_Numeric'] = pd.to_numeric(apt_reset['Bedrooms'], errors='coerce')

# --- 2. Select numeric columns for correlation ---
corr_cols = ['Rent', 'Sqft', 'Amenities_Count', 'Bedrooms_Numeric']
corr_df = apt_reset[corr_cols]

# --- 3. Compute correlation matrix ---
corr_matrix = corr_df.corr()

# --- 4. Plot heatmap ---
plt.figure(figsize=(8,6))
sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt=".2f")
plt.title('Correlation Heatmap')
plt.show()

# Get all unique bedroom types
bedroom_types = apt_reset['Bedrooms'].unique()

# Determine grid size
n = len(bedroom_types)
cols = 2  # adjust number of columns per row
rows = math.ceil(n / cols)

# Create subplots
fig, axes = plt.subplots(rows, cols, figsize=(cols*6, rows*5))
axes = axes.flatten()  # flatten in case of 1 row

for i, b in enumerate(bedroom_types):
    subset = apt_reset[apt_reset['Bedrooms'] == b]
    
    corr_cols_b = ['Rent', 'Sqft', 'Amenities_Count']
    
    # Skip if less than 2 rows
    if subset[corr_cols_b].dropna().shape[0] < 2:
        continue

    corr_matrix_b = subset[corr_cols_b].corr()
    
    sns.heatmap(corr_matrix_b, annot=True, cmap='coolwarm', fmt=".2f", ax=axes[i])
    axes[i].set_title(f'Bedroom Type: {b}')

# Turn off any empty subplots
for j in range(i+1, len(axes)):
    axes[j].axis('off')

plt.tight_layout()
plt.show()

	Complex	Address	Unit_Variant	Bedrooms	Bathrooms	Rent	Sqft	Amenities	Website
0	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	S01	Studio	1.0	1469.0	651.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
1	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A01	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
2	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A02	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
3	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A03	1	1.0	1532.0	801.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
4	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A04	1	1.0	1766.0	861.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
...	...	...	...	...	...	...	...	...	...
251	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B3	2	2.0	2009.0	1069.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
252	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B4	2	2.0	2315.0	1113.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
253	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B5	2	2.0	2150.0	1149.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
254	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B6	2	2.0	2572.0	1208.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
255	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B7	2	2.0	2714.0	1240.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/

	Complex	Address	Unit_Variant	Bedrooms	Bathrooms	Rent	Sqft	Amenities	Website
0	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	S01	0	1.0	1469.0	651.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
1	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A01	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
2	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A02	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
3	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A03	1	1.0	1532.0	801.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
4	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A04	1	1.0	1766.0	861.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/
...	...	...	...	...	...	...	...	...	...
251	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B3	2	2.0	2009.0	1069.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
252	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B4	2	2.0	2315.0	1113.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
253	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B5	2	2.0	2150.0	1149.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
254	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B6	2	2.0	2572.0	1208.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/
255	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	B7	2	2.0	2714.0	1240.0	In-unit washer/dryer; High-speed internet in common areas; EV charging stations; Resort-style pool; 24-hour fitness center; Sophisticated lounges; Bespoke services; Controlled-access security; Dog...	https://broadstonecraft.com/

	Complex	Address
0	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210
1	Tyvola Tapestry	2051 Establishment Wy, Charlotte, NC 28217
2	The Landon	8200 Riverbirch Dr, Charlotte, NC 28210
3	Hawkins Press	2200 Dunavant St, Charlotte, NC 28203
4	Novel Mallard Creek	9132 Senator Royall Dr, Charlotte, NC 28262
5	Ello House	3615 Tryclan Dr, Charlotte, NC 28217
6	The Henry	404 W 26th St, Charlotte, NC 28206
7	The Leo LoSo	4520 Charlotte Park Drive Charlotte, NC 28217
8	The Perch	718 Gesco St, Charlotte, NC 28208
9	Bond on Mint	1007 S Mint St, Charlotte, NC 28203
10	Solis Midtown	1133 Harding Pl, Charlotte, NC 28204
11	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206

	Complex	Address	Neighborhood
0	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	SouthPark
1	Tyvola Tapestry	2051 Establishment Wy, Charlotte, NC 28217	SouthPark
2	The Landon	8200 Riverbirch Dr, Charlotte, NC 28210	SouthPark
3	Hawkins Press	2200 Dunavant St, Charlotte, NC 28203	South End
4	Novel Mallard Creek	9132 Senator Royall Dr, Charlotte, NC 28262	University City
5	Ello House	3615 Tryclan Dr, Charlotte, NC 28217	South End
6	The Henry	404 W 26th St, Charlotte, NC 28206	NoDa
7	The Leo LoSo	4520 Charlotte Park Drive Charlotte, NC 28217	South End
8	The Perch	718 Gesco St, Charlotte, NC 28208	Uptown
9	Bond on Mint	1007 S Mint St, Charlotte, NC 28203	Uptown
10	Solis Midtown	1133 Harding Pl, Charlotte, NC 28204	West Charlotte
11	Broadstone Craft	1015 N Alexander Street, Charlotte, NC 28206	Uptown

	Complex	Address	Unit_Variant	Bedrooms	Bathrooms	Rent	Sqft	Amenities	Website	Neighborhood
0	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	S01	0	1.0	1469.0	651.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/	SouthPark
1	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A01	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/	SouthPark
2	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A02	1	1.0	NaN	747.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/	SouthPark
3	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A03	1	1.0	1532.0	801.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/	SouthPark
4	Moderna Liberty Row	7740 Liberty Row Dr, Charlotte, NC 28210	A04	1	1.0	1766.0	861.0	In-unit washer/dryer; High-speed internet in common areas; Controlled access bicycle storage; Additional storage available; Resort-style pool; 24-hour fitness center; Game room with billiards, pok...	https://www.moderalibertyrow.com/	SouthPark

Data Loading and Cleaning¶

Geolocation Mapping¶

Descriptive Statistics¶

How Bedroom Count Influences Rent, Space, and Market Segmentation¶

How Charlotte's Apartment Complexes Stack Up¶

What the Data Reveals About Charlotte's Neighborhoods¶

What the Data Tells Us About Charlotte’s Rental Landscape¶

Rent Distributions & Variability¶

How much Rents Vary Within Each Complex¶

How Rent Varability Reveals Market Positioning¶

Where Most Rents Actually Fall¶

What the Boxplot Revelas About Rent Distribution¶

How Rent Changes with Bedroom Count¶

What the Boxplot Reveals About Neighborhood Pricing¶

Overall Insights on Rent Distributions and Varability¶

Price per Square Foot Analysis¶

What Price Per Square Foot Reveals About Market Strategy¶

What the Scatter Plot Reveals About PPSF and Market Dynamics¶

Overall Insights on Price Per Square Foot¶

Amenities Insights¶

Unit Size Insights¶

What Bedroom-Normalized Unit Size Reveals About Market Strategy¶

What Square Footage per Bedroom Reveals About Spatial Design¶

What Square Footage per Bedroom Reveals About Complex-Level Design¶

What Rent vs. Square Footage per Bedroom Reveals About Neighborhood Value¶

Overall Insights on Unit Size and Market Strategy¶

Outlier Detection¶

What Z-Score Outlier Detection Reveals About Rent Extremes¶

What IQR-Based Outlier Detection Reveals About Rent Variability¶

What Rent Distributions by Bedroom Type Reveals About Market Dymanics¶

Overall Insights on Outlier Detection¶

Correlations¶

What the Correlation Heatmap Reveals About Housing Relationships¶

What Per-Bedroom Correlation Heatmaps Reveal About Rent Drivers¶

Overall Insights on Correlation Patterns in Rental Housing Data¶

What Descriptive Statistics Reveal About Charlotte's Rental Market¶

	Neighborhood	Landmark	Address
0	Uptown	Bank of America Stadium	800 S Mint St, Charlotte, NC 28202
1	South End	Atherton Mill & Market	2140 South Blvd, Charlotte, NC 28203
2	NoDa	The Evening Muse	322 E 36th St, Charlotte, NC 28205
3	SouthPark	SouthPark Mall	4400 Sharon Rd, Charlotte, NC 28211
4	University City	UNC Charlotte Main Campus	9201 University City Blvd, Charlotte, NC 28223
5	West Charlotte	Freedom Park	1900 East Blvd, Charlotte, NC 28203
6	South Charlotte	Carowinds Theme Park	14523 Carowinds Blvd, Charlotte, NC 28273

	Bedrooms	Mean_Rent	Median_Rent	Min_Rent	Max_Rent	Std_Rent	Mean_Sqft	Median_Sqft	Price_per_Sqft
0	0	1593.108696	1594.0	1064.0	2009.0	257.541169	582.043478	580.0	2.738629
1	1	1768.569081	1707.0	1180.0	3594.0	393.083449	745.586777	729.0	2.397658
2	2	2316.206074	2287.0	1260.0	4179.0	681.126088	1158.813253	1130.0	2.000226
3	3	2392.083333	2358.0	1680.0	3890.0	708.584344	1345.833333	1355.0	1.772169

	Complex	Mean_Rent	Median_Rent	Min_Rent	Max_Rent	Mean_Sqft	Amenities_Count
0	Bond on Mint	2619.086957	2379.000000	1799.0	4179.0	880.891304	13.0
1	Broadstone Craft	1856.945455	1717.000000	1349.0	2714.0	821.954545	13.0
2	Ello House	2083.564008	1847.500000	1490.0	3225.0	864.205128	14.0
3	Hawkins Press	2322.000000	2279.500000	1594.0	3811.0	830.111111	14.0
4	Moderna Liberty Row	2089.925926	2041.000000	1469.0	3487.0	1082.888889	13.0
5	Novel Mallard Creek	1869.533333	1640.000000	1375.0	2350.0	890.000000	15.0
6	Solis Midtown	2509.750000	2460.000000	1394.0	4115.0	894.000000	14.0
7	The Henry	1515.000000	1438.000000	1260.0	2415.0	825.454545	14.0
8	The Landon	1381.153846	1346.666667	1180.0	1690.0	1070.384615	12.0
9	The Leo LoSo	1753.846154	1775.000000	1320.0	2345.0	990.615385	12.0
10	The Perch	1807.083333	1477.500000	1247.5	2565.0	876.833333	10.0
11	Tyvola Tapestry	1692.777778	1637.000000	1064.0	2426.0	872.111111	12.0

	Neighborhood	Mean_Rent	Median_Rent	Mean_Sqft	Units_Count
0	NoDa	1515.000000	1438.0	825.454545	11
1	South End	2031.987908	1847.5	896.409639	83
2	SouthPark	1674.786164	1637.0	1040.962264	53
3	University City	1869.533333	1640.0	890.000000	15
4	Uptown	2120.941270	1950.0	859.150794	63
5	West Charlotte	2509.750000	2460.0	894.000000	20

	Complex	Mean_Rent	Std_Rent	Rent_CV
0	Bond on Mint	2619.086957	743.934620	0.284043
1	Broadstone Craft	1856.945455	359.351353	0.193517
2	Ello House	2083.564008	428.794175	0.205798
3	Hawkins Press	2322.000000	573.760762	0.247098
4	Moderna Liberty Row	2089.925926	510.671892	0.244349
5	Novel Mallard Creek	1869.533333	370.476501	0.198165
6	Solis Midtown	2509.750000	807.980906	0.321937
7	The Henry	1515.000000	318.123247	0.209982
8	The Landon	1381.153846	186.234481	0.134840
9	The Leo LoSo	1753.846154	293.412023	0.167296
10	The Perch	1807.083333	444.748979	0.246114
11	Tyvola Tapestry	1692.777778	456.744397	0.269819

	Complex	25th_Percentile	75th_Percentile
0	Bond on Mint	1979.000000	3309.000
1	Broadstone Craft	1679.200000	2006.000
2	Ello House	1838.323529	2555.000
3	Hawkins Press	1910.750000	2557.750
4	Moderna Liberty Row	1707.000000	2337.000
5	Novel Mallard Creek	1581.000000	2270.000
6	Solis Midtown	1843.750000	2870.750
7	The Henry	1353.000000	1511.500
8	The Landon	1211.250000	1490.000
9	The Leo LoSo	1520.000000	1890.000
10	The Perch	1475.000000	2140.625
11	Tyvola Tapestry	1385.000000	1787.000

	Complex	Bedrooms	Mean_Sqft_per_Bedroom	Median_Sqft_per_Bedroom	Min_Sqft_per_Bedroom	Max_Sqft_per_Bedroom	Std_Sqft_per_Bedroom
0	Bond on Mint	1	740.0	746.0	659.0	801.0	52.089666
1	Bond on Mint	2	602.861111	557.5	541.5	764.5	89.498177
2	Broadstone Craft	1	697.785714	670.0	560.0	895.0	96.505224
3	Broadstone Craft	2	551.714286	556.5	479.0	620.0	53.09022
4	Ello House	1	742.0	746.0	558.0	989.0	98.623114
5	Ello House	2	587.636364	573.0	527.5	714.5	50.558922
6	Hawkins Press	1	774.6	830.5	582.0	861.0	104.010897
7	Hawkins Press	2	518.75	541.75	438.5	553.0	54.003858
8	Hawkins Press	3	449.333333	449.333333	449.333333	449.333333	<NA>
9	Moderna Liberty Row	1	912.625	881.5	747.0	1333.0	189.607819
10	Moderna Liberty Row	2	633.625	623.5	562.0	703.5	49.19041
11	Moderna Liberty Row	3	467.333333	467.333333	467.333333	467.333333	<NA>
12	Novel Mallard Creek	1	768.333333	735.0	689.0	980.0	113.164777
13	Novel Mallard Creek	2	571.666667	565.25	539.0	614.5	24.963306
14	Solis Midtown	1	802.888889	797.0	627.0	999.0	128.171218
15	Solis Midtown	2	585.416667	549.0	499.0	707.5	83.219239
16	Solis Midtown	3	478.333333	478.333333	478.333333	478.333333	<NA>
17	The Henry	1	723.857143	740.0	656.0	778.0	47.642518
18	The Henry	2	548.25	548.25	544.5	552.0	5.303301
19	The Henry	3	413.333333	413.333333	413.333333	413.333333	<NA>
20	The Landon	1	799.5	782.5	715.0	918.0	88.616348
21	The Landon	2	570.583333	554.25	496.0	676.0	69.00752
22	The Landon	3	430.0	432.333333	350.333333	500.333333	48.639719
23	The Leo LoSo	1	703.916667	724.0	531.0	807.0	91.124748
24	The Leo LoSo	2	595.590909	608.0	543.5	614.0	27.861998
25	The Leo LoSo	3	467.333333	467.333333	467.333333	467.333333	0.0
26	The Perch	1	639.375	668.0	459.0	789.0	120.175987
27	The Perch	2	543.4	520.5	493.0	617.0	54.698492
28	The Perch	3	458.444444	453.666667	449.666667	472.0	11.908603
29	Tyvola Tapestry	1	645.75	665.5	570.0	682.0	51.564684
30	Tyvola Tapestry	2	520.25	520.25	513.5	527.0	9.545942
31	Tyvola Tapestry	3	454.666667	454.666667	442.666667	466.666667	16.970563