%pip install numpy pandas lightningchart

Downloaded the dataset from Kaggle - https://www.kaggle.com/datasets/khushikyad001/china-water-pollution-monitoring-dataset

# Import necessary libraries (load pandas library to preprocess dataset)
import pandas as pd

# Name the dataset as cwpd = China Water Pollution Data
cwpd = pd.read_csv("china_water_pollution_data.csv")

# Get basic information about the China Water Pollution Monitoring Dataset
cwpd.info()

# Check for missing values
cwpd.isnull().sum()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import lightningchart as lc
import pandas as pd
from datetime import datetime

# Load license key securely from file
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()

# Set your LightningChart license key
lc.set_license(license_key)

# Load dataset
df = pd.read_csv("china_water_pollution_data.csv")

# Parse and clean 'Date' column
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')  # force invalid dates to NaT
df = df.dropna(subset=['Date'])                           # drop rows where date is invalid

# Sort and group by date
df = df.sort_values('Date')
grouped = df.groupby('Date')['COD_mg_L'].mean().reset_index()

# Convert to UNIX timestamps for x-axis
grouped['Timestamp'] = grouped['Date'].apply(lambda d: d.timestamp() * 1000)
x_values = grouped['Timestamp'].tolist()
y_values = grouped['COD_mg_L'].fillna(0).astype(float).tolist()

# Chart setup
chart = lc.ChartXY(
    theme=lc.Themes.Light,
    title='Average COD Levels Over Time (2023)'
)

series = chart.add_line_series()
series.add(x=x_values, y=y_values)
series.set_line_thickness(2)
series.set_line_color(lc.Color('green'))

# Correct axis titles and strategy
chart.get_default_x_axis().set_title("Date")
chart.get_default_y_axis().set_title("COD (mg/L)")
chart.get_default_x_axis().set_tick_strategy('DateTime')

# Show chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import lightningchart as lc
import pandas as pd
from datetime import datetime

# Load license key securely from file
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()

# Set your license key
lc.set_license(license_key)

# Load data
df = pd.read_csv("china_water_pollution_data.csv")

# Parse and clean 'Date' column
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')  # force invalid dates to NaT
df = df.dropna(subset=['Date'])                           # drop rows where date is invalid

# Sort and group by date
df = df.sort_values('Date')
grouped = df.groupby('Date')['BOD_mg_L'].mean().reset_index()

# Convert to UNIX timestamps for x-axis
grouped['Timestamp'] = grouped['Date'].apply(lambda d: d.timestamp() * 1000)
x_values = grouped['Timestamp'].tolist()
y_values = grouped['BOD_mg_L'].fillna(0).astype(float).tolist()

# Chart setup
chart = lc.ChartXY(
    theme=lc.Themes.Light,
    title='Average BOD Levels Over Time (2023)'
)

series = chart.add_line_series()
series.add(x=x_values, y=y_values)
series.set_line_thickness(2)
series.set_line_color(lc.Color('blue'))

# Correct axis titles and strategy
chart.get_default_x_axis().set_title("Date")
chart.get_default_y_axis().set_title("BOD (mg/L)")
chart.get_default_x_axis().set_tick_strategy('DateTime')

# Show chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import lightningchart as lc
import pandas as pd

# Load license key securely from file
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()

# Set license key
lc.set_license(license_key)

# Load dataset
df = pd.read_csv("china_water_pollution_data.csv")

# Parse and clean 'Date' column
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
df = df.dropna(subset=['Date'])

# Sort and group by date
df = df.sort_values('Date')
grouped = df.groupby('Date')[['COD_mg_L', 'BOD_mg_L']].mean().reset_index()

# Convert to UNIX timestamps for x-axis
grouped['Timestamp'] = grouped['Date'].apply(lambda d: d.timestamp() * 1000)

# Prepare x and y values
x_values = grouped['Timestamp'].tolist()
cod_values = grouped['COD_mg_L'].fillna(0).astype(float).tolist()
bod_values = grouped['BOD_mg_L'].fillna(0).astype(float).tolist()

# Create chart
chart = lc.ChartXY(
    theme=lc.Themes.Light,
    title='COD and BOD Levels Over Time (Point Line Series)'
)

# COD series with circle points
cod_series = chart.add_point_line_series()
cod_series.set_point_shape('circle')
cod_series.set_point_size(6)
cod_series.set_point_color(lc.Color('green'))
cod_series.set_line_color(lc.Color('green'))
cod_series.set_line_thickness(2)
cod_series.add(x=x_values, y=cod_values)

# BOD series with triangle points
bod_series = chart.add_point_line_series()
bod_series.set_point_shape('triangle')
bod_series.set_point_size(6)
bod_series.set_point_color(lc.Color('blue'))
bod_series.set_line_color(lc.Color('blue'))
bod_series.set_line_thickness(2)
bod_series.add(x=x_values, y=bod_values)

# Axis configuration
chart.get_default_x_axis().set_title("Date")
chart.get_default_y_axis().set_title("Pollutant Level (mg/L)")
chart.get_default_x_axis().set_tick_strategy('DateTime')

# Show chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import pandas as pd
import lightningchart as lc
import numpy as np

# Load license
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

df = pd.read_csv("china_water_pollution_data.csv")
df = df.dropna(subset=['COD_mg_L', 'BOD_mg_L'])

cod = df['COD_mg_L'].astype(float).tolist()
bod = df['BOD_mg_L'].astype(float).tolist()

chart = lc.ChartXY(title="Scatter Plot: COD vs BOD", theme=lc.Themes.Light)
series = chart.add_point_series()

# Set fallback color
series.set_point_color(lc.Color('gray'))

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
# Set wider fixed color steps
series.set_palette_point_coloring(
    steps=[
        {'value': 1.0, 'color': lc.Color('blue')},
        {'value': 2.5, 'color': lc.Color('cyan')},
        {'value': 4.0, 'color': lc.Color('green')},
        {'value': 6.0, 'color': lc.Color('yellow')},
        {'value': 9.0, 'color': lc.Color('red')}
    ],
    look_up_property='y',
    percentage_values=False
)

series.add(x=cod, y=bod)
chart.get_default_x_axis().set_title("COD (mg/L)")
chart.get_default_y_axis().set_title("BOD (mg/L)")
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import pandas as pd
import lightningchart as lc
import numpy as np

# Load license
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

df = pd.read_csv("china_water_pollution_data.csv")

df = df.dropna(subset=['Total_Phosphorus_mg_L', 'Total_Nitrogen_mg_L'])
x_vals = df['Total_Phosphorus_mg_L'].astype(float).tolist()
y_vals = df['Total_Nitrogen_mg_L'].astype(float).tolist()

chart = lc.ChartXY(title="Scatter Plot: Total Phosphorus vs Total Nitrogen", theme=lc.Themes.Light)
series = chart.add_point_series()

# Fallback default color
series.set_point_color(lc.Color('gray'))

# Use fixed broader ranges
series.set_palette_point_coloring(
    steps=[
        {'value': 1, 'color': lc.Color('blue')},
        {'value': 3, 'color': lc.Color('cyan')},
        {'value': 5, 'color': lc.Color('green')},
        {'value': 7, 'color': lc.Color('yellow')},
        {'value': 9, 'color': lc.Color('red')}
    ],
    look_up_property='y',
    percentage_values=False
)

series.add(x=x_vals, y=y_vals)
chart.get_default_x_axis().set_title("Total Phosphorus (mg/L)")
chart.get_default_y_axis().set_title("Total Nitrogen (mg/L)")
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import pandas as pd
import numpy as np
import lightningchart as lc

# Load license key
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
# Load data
df = pd.read_csv("china_water_pollution_data.csv")
df = df.dropna(subset=['COD_mg_L', 'Province'])

# Group data
provinces = sorted(df['Province'].unique())
category_data = {prov: df[df['Province'] == prov]['COD_mg_L'].astype(float).tolist() for prov in provinces}

# Create chart
chart = lc.ChartXY(title='Box Plot of COD Levels Across Provinces', theme=lc.Themes.Light)

# Prepare box series
dataset = []
x_outliers, y_outliers = [], []

for i, province in enumerate(provinces):
    values = category_data[province]
    if len(values) < 5:
        continue  # Skip categories with very few data points

    start = (i * 2) + 1
    end = start + 1
    Q1 = np.percentile(values, 25)
    Q3 = np.percentile(values, 75)
    median = np.median(values)
    IQR = Q3 - Q1

    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR

    # Adjust whiskers to match standard box plot definition
    non_outliers = [v for v in values if lower_bound <= v <= upper_bound]
    lower_whisker = min(non_outliers)
    upper_whisker = max(non_outliers)

    dataset.append({
        'start': start,
        'end': end,
        'lowerQuartile': Q1,
        'upperQuartile': Q3,
        'median': median,
        'lowerExtreme': lower_whisker,
        'upperExtreme': upper_whisker
    })

    # Add outliers
    outliers = [v for v in values if v < lower_bound or v > upper_bound]
    x_outliers.extend([start + 0.5] * len(outliers))
    y_outliers.extend(outliers)

# Add to chart
box_series = chart.add_box_series()
box_series.add_multiple(dataset)

outlier_series = chart.add_point_series(sizes=True)
outlier_series.set_point_color(lc.Color('red'))
outlier_series.append_samples(x_values=x_outliers, y_values=y_outliers, sizes=[10] * len(y_outliers))

# Add axis labels
chart.get_default_x_axis().set_title("Provinces (by position index)")
chart.get_default_y_axis().set_title("COD (mg/L)")

# Print province mapping
print("Province X-Axis Mapping:")
for i, province in enumerate(provinces):
    print(f"{(i * 2) + 1.5}: {province}")

# Open chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import pandas as pd
import numpy as np
import lightningchart as lc

# Load license key
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()    
lc.set_license(license_key)

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
# Load dataset
df = pd.read_csv("china_water_pollution_data.csv")

# Clean and preprocess
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
df = df.dropna(subset=['Date', 'Province', 'COD_mg_L'])
df['Month'] = df['Date'].dt.to_period('M').astype(str)

# Map months and provinces to indices
month_list = sorted(df['Month'].unique())
province_list = sorted(df['Province'].unique())

month_map = {m: i for i, m in enumerate(month_list)}
province_map = {p: i for i, p in enumerate(province_list)}

df['MonthIndex'] = df['Month'].map(month_map)
df['ProvinceIndex'] = df['Province'].map(province_map)

# Group by Month and Province
grouped = df.groupby(['MonthIndex', 'ProvinceIndex'])['COD_mg_L'].mean().reset_index()

# Create bubble chart data
bubble_data = []
for _, row in grouped.iterrows():
    cod = row['COD_mg_L']
    bubble_data.append({
        'x': row['MonthIndex'],
        'y': row['ProvinceIndex'],
        'z': cod,
        'size': cod,
        'value': cod
    })

# Create 3D Chart
chart = lc.Chart3D(title="3D Bubble Chart: COD Levels Across Provinces and Time", theme=lc.Themes.Light)

# Set axis titles
chart.get_default_x_axis().set_title("Month Index")
chart.get_default_y_axis().set_title("Province Index")
chart.get_default_z_axis().set_title("COD (mg/L)")

# Add point series
series = chart.add_point_series(
    render_2d=False,
    individual_lookup_values_enabled=True,
    individual_point_color_enabled=True,
    individual_point_size_axis_enabled=True,
    individual_point_size_enabled=True,
)
series.set_point_shape('sphere')

# Color palette based on COD intensity
series.set_palette_point_colors(
    steps=[
        {'value': grouped['COD_mg_L'].min(), 'color': lc.Color('blue')},
        {'value': grouped['COD_mg_L'].quantile(0.25), 'color': lc.Color('cyan')},
        {'value': grouped['COD_mg_L'].median(), 'color': lc.Color('green')},
        {'value': grouped['COD_mg_L'].quantile(0.75), 'color': lc.Color('yellow')},
        {'value': grouped['COD_mg_L'].max(), 'color': lc.Color('red')}
    ],
    look_up_property='value',
    interpolate=True,
    percentage_values=False
)

# Add data
series.add(bubble_data)

# Show chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import lightningchart as lc
import pandas as pd
import numpy as np

# Load license
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
    
lc.set_license(license_key)

# Load data
df = pd.read_csv("china_water_pollution_data.csv")

# Clean and preprocess
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
df = df.dropna(subset=['Date', 'Ammonia_N_mg_L', 'Total_Phosphorus_mg_L',
                       'Total_Nitrogen_mg_L', 'COD_mg_L', 'BOD_mg_L'])
df['Month'] = df['Date'].dt.to_period('M').astype(str)

# Group and average
monthly_avg = df.groupby('Month')[['Ammonia_N_mg_L', 'Total_Phosphorus_mg_L',
                                   'Total_Nitrogen_mg_L', 'COD_mg_L', 'BOD_mg_L']].mean()
monthly_avg = monthly_avg.sort_index()
months = list(monthly_avg.index)
x_values = list(range(len(months)))

# Stack pollutant data
ammonia = monthly_avg['Ammonia_N_mg_L'].values
phosphorus = ammonia + monthly_avg['Total_Phosphorus_mg_L'].values
nitrogen = phosphorus + monthly_avg['Total_Nitrogen_mg_L'].values
cod = nitrogen + monthly_avg['COD_mg_L'].values
bod = cod + monthly_avg['BOD_mg_L'].values

# Create chart
chart = lc.ChartXY(theme=lc.Themes.Light, title="Monthly Stacked Pollutant Levels")

# Add stacked area series
series1 = chart.add_area_series()
series1.set_name("Ammonia (mg/L)")
series1.add(x_values, ammonia)

series2 = chart.add_area_series()
series2.set_name("Total Phosphorus (mg/L)")
series2.add(x_values, phosphorus)

series3 = chart.add_area_series()
series3.set_name("Total Nitrogen (mg/L)")
series3.add(x_values, nitrogen)

series4 = chart.add_area_series()
series4.set_name("COD (mg/L)")
series4.add(x_values, cod)

series5 = chart.add_area_series()
series5.set_name("BOD (mg/L)")
series5.add(x_values, bod)

# Configure axes
chart.get_default_x_axis().set_title("Month (Index)")
chart.get_default_y_axis().set_title("Cumulative Pollutant Level (mg/L)")

# Print month index mapping for reference
for i, month in enumerate(months):
    print(f"{i}: {month}")

# Show chart
chart.open()

# Developed with AI assistance to showcase the performance of LightningChart Python libraries.
import pandas as pd
import lightningchart as lc

# Load license key
with open("D:/Vindy/HAMK/Internship/MyProjects/lc_license.txt", "r") as f:
    license_key = f.read().strip()
lc.set_license(license_key)

# Load and preprocess dataset
df = pd.read_csv("china_water_pollution_data.csv")
df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
df = df.dropna(subset=[
    'Date', 'Ammonia_N_mg_L', 'Total_Phosphorus_mg_L',
    'Total_Nitrogen_mg_L', 'COD_mg_L', 'BOD_mg_L'
])
df['Month'] = df['Date'].dt.to_period('M').astype(str)

# Calculate monthly averages
monthly_avg = df.groupby('Month')[[
    'Ammonia_N_mg_L', 'Total_Phosphorus_mg_L',
    'Total_Nitrogen_mg_L', 'COD_mg_L', 'BOD_mg_L'
]].mean()
monthly_avg = monthly_avg.sort_index()

# Prepare data for chart
months = list(monthly_avg.index)
data_grouped = [
    {'subCategory': 'Ammonia', 'values': monthly_avg['Ammonia_N_mg_L'].tolist()},
    {'subCategory': 'Total Phosphorus', 'values': monthly_avg['Total_Phosphorus_mg_L'].tolist()},
    {'subCategory': 'Total Nitrogen', 'values': monthly_avg['Total_Nitrogen_mg_L'].tolist()},
    {'subCategory': 'COD', 'values': monthly_avg['COD_mg_L'].tolist()},
    {'subCategory': 'BOD', 'values': monthly_avg['BOD_mg_L'].tolist()},
]

# Create bar chart
chart = lc.BarChart(
    vertical=True,
    theme=lc.Themes.Light,
    title="Grouped Monthly Pollutant Levels (Y-axis: mg/L)"
)
chart.set_data_grouped(months, data_grouped)

# Show chart
chart.open()