smzn

import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA

# Excluding the target variable 'Diabetes_binary' for PCA
features = data.drop('Diabetes_binary', axis=1)

# Scaling the data
scaler = StandardScaler()
scaled_features = scaler.fit_transform(features)

smzn

# Re-importing necessary libraries and reloading the data
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import itertools

# Function to determine if a column is binary
def is_binary(column):
    return sorted(column.unique()) == [0, 1]

smzn

# Identifying binary columns in the dataset
binary_columns = [col for col in data.columns if is_binary(data[col])]

# Creating combinations of binary and non-binary numeric columns for box plots
binary_non_binary_combinations = list(itertools.product(binary_columns, non_binary_numeric_columns))

# Setting up the plotting grid for these combinations
n_plots = len(binary_non_binary_combinations)
n_cols = 3  # Number of columns per row
n_rows = (n_plots + n_cols - 1) // n_cols  # Calculating the required number of rows

smzn

# Re-importing necessary libraries and reloading the data
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import itertools

# Function to determine if a column is binary
def is_binary(column):
    return sorted(column.unique()) == [0, 1]

smzn

import matplotlib.pyplot as plt
import seaborn as sns

# Set the aesthetic style of the plots
sns.set_style("whitegrid")

# Selecting a subset of columns for plotting histograms
# Excluding binary columns for more meaningful histograms
hist_columns = [
    "Diabetes_binary",

smzn

import matplotlib.pyplot as plt
import seaborn as sns

# Set the aesthetic style of the plots
sns.set_style("whitegrid")

# Selecting a subset of columns for plotting histograms
# Excluding binary columns for more meaningful histograms
hist_columns = ['BMI', 'Age', 'GenHlth', 'MentHlth', 'PhysHlth', 'Education', 'Income']

smzn

import pandas as pd

# Load the dataset
file_path = '/content/drive/MyDrive/研究/糖尿病/Diabetes Health Indicators Dataset/diabetes_binary_health_indicators_BRFSS2015.csv'
data = pd.read_csv(file_path)

# Display the first few rows of the dataset
data

# Checking data types and unique values for each column

smzn

# Aligning the station names exactly with the transition probability matrix, excluding any extra stations
# First, we adjust the list of station names to exclude the extra station (if any)
aligned_stations = set(transition_probability_matrix.columns) - {'start_station_name'}

# Filter the station_stats dataframe to include only those rows where both the start and end stations are in the aligned_stations set
filtered_station_stats = station_stats[
    (station_stats['start_station_name'].isin(aligned_stations)) & 
    (station_stats['end_station_name'].isin(aligned_stations))
]

smzn

import pandas as pd

df = divvy_tripdata

# 2. Convert 'started_at' and 'ended_at' to datetime
df['started_at'] = pd.to_datetime(df['started_at'])
df['ended_at'] = pd.to_datetime(df['ended_at'])

# 3. Calculate the travel time for each trip
df['travel_time'] = df['ended_at'] - df['started_at']

smzn

import matplotlib.pyplot as plt
import seaborn as sns

# Set the size of the heatmap
plt.figure(figsize=(20, 15))

# Adjust the heatmap color mapping to use red for high values and white for low values
plt.figure(figsize=(20, 15))
sns.heatmap(transition_probability_matrix.iloc[:, 1:], cmap='Reds')