import pandas as pd
from plotnine import *

# Following Grammar of Graphics exactly:
# Data (mpg) -> Aesthetics (x,y,color) -> Geometries (point, smooth)
plot = (
    ggplot(mpg, aes(x='displ', y='hwy', color='class'))
    + geom_point(size=3, alpha=0.7)
    + geom_smooth(method='lm', se=False) # Add regression line
    + theme_minimal()                    # Add theme
    + labs(title='Engine Displacement vs Highway MPG')
)
print(plot)

import matplotlib.pyplot as plt

# 1. Create the Figure (The Canvas) and Axes (The Artist)
fig, ax = plt.subplots(figsize=(10, 6), dpi=100)

# 2. Draw on the Axes
ax.plot([1, 2, 3], [4, 5, 2], marker='o', label='Data A')

# 3. Configure the Axes (Anatomy elements)
ax.set_title("My First OOP Plot", fontsize=16, fontweight='bold')
ax.set_xlabel("X-Axis (Units)", fontsize=12)
ax.set_ylabel("Y-Axis (Units)", fontsize=12)

# Set limits and ticks
ax.set_xlim(0, 4)
ax.set_ylim(0, 6)
ax.grid(True, linestyle='--', alpha=0.7)

# 4. Add accessories
ax.legend(loc='upper right')

# 5. Render or Save
plt.tight_layout() # Prevent clipping
plt.show()
# fig.savefig('my_plot.png', dpi=300)

import matplotlib.pyplot as plt
import numpy as np

fig, axs = plt.subplots(1, 2, figsize=(15, 5))

# 1. Scatter Plot (Color & Size mapping)
x = np.random.randn(100)
y = x + np.random.randn(100)*0.5
sizes = np.random.uniform(10, 200, 100)
colors = x

sc = axs[0].scatter(x, y, s=sizes, c=colors, cmap='viridis', alpha=0.7)
axs[0].set_title('Scatter Plot')
fig.colorbar(sc, ax=axs[0], label='Color Value')

# 2. Bar Chart (with Error Bars)
categories = ['Group A', 'Group B', 'Group C']
values = [10, 22, 15]
errors = [1.5, 3.0, 2.0]

axs[1].bar(categories, values, yerr=errors, capsize=5, color='coral', alpha=0.8)
axs[1].set_title('Bar Chart with Error Bars')
for i, v in enumerate(values):
    axs[1].text(i, v + 0.5, str(v), ha='center')

plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec

fig = plt.figure(figsize=(10, 8))
gs = gridspec.GridSpec(3, 3, figure=fig)

# 1. Main large plot (spans 2x2 grid)
ax_main = fig.add_subplot(gs[0:2, 0:2])
ax_main.set_title('Main View')

# 2. Side plots (Top right, Bottom right)
ax_side1 = fig.add_subplot(gs[0, 2])
ax_side2 = fig.add_subplot(gs[1, 2])

# 3. Bottom wide plot (spans 1x3 grid)
ax_bottom = fig.add_subplot(gs[2, :])
ax_bottom.set_title('Timeline View')

plt.tight_layout()
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns

# 1. Apply a global Seaborn theme
sns.set_theme(style="whitegrid", palette="muted")

# 2. Customize fonts globally
plt.rcParams.update({
    'font.family': 'sans-serif',
    'font.sans-serif': ['Helvetica', 'Arial'],
    'axes.titleweight': 'bold',
    'axes.titlesize': 16,
    'axes.labelsize': 12,
    'lines.linewidth': 2
})

# 3. Plotting with the new theme
fig, ax = plt.subplots(figsize=(8, 5))
ax.plot([1, 2, 3], [4, 5, 2], label='Data')
ax.legend()

# 4. Remove top and right spines (cleaner look)
sns.despine(ax=ax)

plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

penguins = sns.load_dataset("penguins")

fig, axes = plt.subplots(1, 2, figsize=(12, 5))

# 1. Histogram + KDE overlay
sns.histplot(
    data=penguins, x="flipper_length_mm", hue="species",
    element="step", stat="density", common_norm=False,
    ax=axes[0]
)
axes[0].set_title("Histogram with Step Fill")

# 2. KDE Plot with Rug Plot
sns.kdeplot(
    data=penguins, x="body_mass_g", hue="species",
    fill=True, common_norm=False, palette="crest",
    alpha=0.5, linewidth=1.5, ax=axes[1]
)
sns.rugplot(
    data=penguins, x="body_mass_g", hue="species",
    height=0.05, ax=axes[1]
)
axes[1].set_title("KDE Density + Rug Plot")

sns.despine()
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset("tips")

# 1. Advanced Scatter (4 dimensions: x, y, color, size)
plt.figure(figsize=(8, 6))
sns.scatterplot(
    data=tips, x="total_bill", y="tip",
    hue="time", size="size", sizes=(20, 200),
    palette="deep", alpha=0.8
)
plt.title("4D Scatter Plot (Total Bill vs Tip)")
plt.show()

# 2. Regression Plot with Subplots (Using lmplot)
# lmplot is a figure-level function that creates multiple subplots automatically
sns.lmplot(
    data=tips, x="total_bill", y="tip", col="time", hue="smoker",
    height=5, aspect=1.2, scatter_kws={'alpha':0.5}
)
plt.show()

# 3. Pairplot (Explore all pairwise relationships)
sns.pairplot(
    data=tips, hue="smoker",
    diag_kind="kde", markers=["o", "s"]
)
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset("tips")
fig, axes = plt.subplots(1, 2, figsize=(14, 6))

# 1. Violin Plot (Distribution density across categories)
sns.violinplot(
    data=tips, x="day", y="total_bill", hue="sex",
    split=True, inner="quart", palette="muted",
    ax=axes[0]
)
axes[0].set_title("Violin Plot (Split by Sex)")

# 2. Boxplot + Swarmplot Overlay
# Good for showing summary stats PLUS underlying data points
sns.boxplot(
    data=tips, x="day", y="total_bill", color="white",
    width=.5, showfliers=False, ax=axes[1] # hide boxplot outliers to avoid overlap
)
sns.swarmplot(
    data=tips, x="day", y="total_bill", hue="time",
    size=6, alpha=0.7, ax=axes[1]
)
axes[1].set_title("Boxplot + Swarmplot Overlay")

plt.tight_layout()
plt.show()

import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

# Load data and calculate correlation matrix
penguins = sns.load_dataset("penguins")
# Select only numerical columns for correlation
numerical_df = penguins.select_dtypes(include=[np.number]) 
corr = numerical_df.corr()

# Create a mask for the upper triangle
mask = np.triu(np.ones_like(corr, dtype=bool))

plt.figure(figsize=(8, 6))

# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(
    corr, 
    mask=mask, 
    cmap='coolwarm', 
    vmax=1, vmin=-1, 
    center=0,
    square=True, 
    linewidths=.5, 
    annot=True, 
    fmt=".2f",
    cbar_kws={"shrink": .8}
)

plt.title("Penguin Feature Correlation")
plt.tight_layout()
plt.show()

import plotly.express as px

df = px.data.gapminder()

# Plotly makes animations incredibly easy with two arguments:
# 'animation_frame' (the time dimension) and 'animation_group' (the entity)
fig = px.scatter(
    df, 
    x="gdpPercap", y="lifeExp", 
    animation_frame="year", animation_group="country",
    size="pop", color="continent", 
    hover_name="country",
    log_x=True, size_max=55, 
    range_x=[100,100000], range_y=[25,90],
    title="Global Development 1952 - 2007"
)

fig.show()

import streamlit as st
import pandas as pd
import plotly.express as px

# 1. Page Configuration
st.set_page_config(page_title="Sales Dashboard", layout="wide")
st.title("Interactive Sales Dashboard 📊")

# 2. Sidebar Filters
st.sidebar.header("Filters")
category = st.sidebar.selectbox("Select Category", ["Electronics", "Clothing", "Home"])
min_sales = st.sidebar.slider("Minimum Sales", 0, 1000, 200)

# Mock Data Generation
df = pd.DataFrame({
    'Date': pd.date_range(start='2023-01-01', periods=30),
    'Sales': [x * 10 for x in range(30)],
    'Category': [category] * 30
})
filtered_df = df[df['Sales'] >= min_sales]

# 3. Layout with Columns
col1, col2 = st.columns(2)

# KPI Metric
col1.metric("Total Filtered Sales", f"${filtered_df['Sales'].sum()}")

# 4. Insert Plotly Chart
fig = px.line(filtered_df, x='Date', y='Sales', title=f"{category} Sales Trend")
col2.plotly_chart(fig, use_container_width=True)

import plotly.express as px

# Plotly includes built-in geospatial data
df = px.data.gapminder().query("year==2007")

# Create a choropleth map
# 'locations' takes ISO-3 country codes by default 
fig = px.choropleth(
    df, 
    locations="iso_alpha",   # Geopolitical boundaries
    color="lifeExp",         # Data to map to color
    hover_name="country",    # Tooltip label
    color_continuous_scale=px.colors.sequential.Plasma,
    title="Global Life Expectancy (2007)"
)

# Customize the map projection type
fig.update_geos(
    projection_type="orthographic", # "natural earth", "mercator", etc.
    showcoastlines=True, 
    coastlinecolor="DarkBlue"
)

fig.show()

import plotly.express as px

# Load Iris dataset
df = px.data.iris()

# Create interactive 3D scatter plot
fig = px.scatter_3d(
    df, 
    x='sepal_length', 
    y='sepal_width', 
    z='petal_width',
    color='species',
    size='petal_length', 
    size_max=18,
    symbol='species',
    opacity=0.7,
    title="Iris 3D Feature Space"
)

# Tight layout for 3D plot
fig.update_layout(margin=dict(l=0, r=0, b=0, t=40))
fig.show()