import pandas as pd
import plotly.graph_objects as gr
data = {
    'Sending_Dept':   ['5A', '4A', '5B', '5A', '4B', '4A', '3A', '3B', '3A', '3B', '3A', '3B'],
    'Accepting_Dept': ['4B', '5B', '5A', '5B', '4A', '4B', '5B', '5A', '4B', '4A', '3B', '3A'],
    'FlowValue': [1, 3, 4, 3, 4, 4, 1, 1, 3, 2, 5, 3]
}
df = pd.DataFrame(data)
unique_departments = set(df['Sending_Dept']).union(set(df['Accepting_Dept']))
Depts = list(unique_departments)
Dept_indices = {}
for i, dept in enumerate(Depts):
    Dept_indices[dept] = i
sending_indices = []
for dept in df['Sending_Dept']:
    dept_index = Dept_indices[dept]
    sending_indices.append(dept_index)
    print(f"Sending indices are: {sending_indices}")
accepting_indices = []
for dept in df['Accepting_Dept']:
    dept_index = Dept_indices[dept]
    accepting_indices.append(dept_index)
flowvalues = df['FlowValue'].tolist()
# Sankey diagram
fig = gr.Figure(data=[gr.Sankey(
    node=dict( pad=10,thickness=25,line=dict(color="red", width=0.8),label=Depts,),
    link=dict(source=sending_indices,target=accepting_indices,value=flowvalues
    ))])
fig.update_layout(title_text="Sankey Diagram of exchange students flow between University Depts", font_size=12)
fig.show()

import matplotlib.pyplot as plt
import numpy as np
np.random.seed(125)
num_houses = 10
distances = np.random.uniform(0, 30, num_houses)  # distance from city center
prices = np.random.uniform(400, 2000, num_houses) * 1000  # sale price in thousands
directions = np.random.choice(['N', 'S', 'E', 'W'], num_houses)  # direction from city center
agent_levels = np.random.choice([1, 2, 3], num_houses)  # agent's level
def get_emoji_size(level):
    size_map = {1: 250, 2: 380, 3: 700}
    return size_map.get(level, 120)  # Increased size for better visibility
def get_emoji_color_new(price):
    if price < 600000:
        return 'white'  # Light yellow for $400k-$600k
    elif price < 800000:
        return 'yellow'        # White for $600k-$800k
    elif price < 1000000:
        return 'pink'         # Pink for $800k-$1 million
    else:
        return 'lime'         # Lime for $1 million-$2 million
def rotate_smiley(direction):
    rotation_map = {'N': 0, 'E': 270, 'S': 180, 'W': 90}
    return rotation_map.get(direction, 0)  # default no rotation if direction not found
plt.figure(figsize=(12, 8))
for i in range(num_houses):
    plt.scatter(distances[i], prices[i], s=get_emoji_size(agent_levels[i]),\
    c=get_emoji_color_new(prices[i]), 
                marker='o', edgecolors='black', alpha=0.8)
    plt.text(distances[i], prices[i], "??", fnotallow=agent_levels[i]*10, 
             rotatinotallow=rotate_smiley(directions[i]), ha='center', va='center',\
             fnotallow='bold')
plt.xlabel('Distance from City Center (km)')
plt.ylabel('Sale Price ($)')
plt.title('House Sales Data for 10 Houses: Price vs Distance with New Color Scheme')
plt.grid(True)
plt.show()

import plotly.graph_objects as go
labels = ["PineForest University", 
          "College of Engineering", "Natural Sciences", "Medical School",
          "Chemical Engineering", "Mechanical Engineering", "Computer Science", "Electrical Engineering",\
          "Biomedical Engineering",
          "Astronomy", "Biology", "Mathematics", "Physics","Chemistry","Statistics","EarthSciences",\
          "Emergency Medicine", "Neurology", "Cardiology", "Pediatrics", "Pathology","Family Medicine", \
          "Orthopedics", "Obstetrics", "Anesthesiology", "Anatomy", "Physiology",\
          "Microbiology","Immunology"]
parents = ["", 
           "PineForest University", "PineForest University", "PineForest University",
           "College of Engineering", "College of Engineering", "College of Engineering",\
           "College of Engineering","College of Engineering",
           "Natural Sciences","Natural Sciences","Natural Sciences","Natural Sciences","Natural Sciences",\
           "Natural Sciences","Natural Sciences",
           "Medical School", "Medical School", "Medical School", "Medical School","Medical School", \
           "Medical School","Medical School", "Medical School", "Medical School",\
           "Medical School", "Medical School", "Medical School","Medical School"]
values = [0, 
          50, 30, 200, 
          85, 100, 180, 163,120,
          90,70 ,104,54,180,100,70,
          70,180,200, 85,170,89,75,120,76,150,67,56,239]
fig = go.Figure(go.Sunburst(
    labels=labels,
    parents=parents,
    values=values,
))
fig.update_layout(margin=dict(t=0, l=0, r=0, b=0))
fig.show()

import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
np.random.seed(0)
size_of_house = np.random.uniform(1000, 4000, 100)  # Size in square feet
price = size_of_house * np.random.uniform(150, 350) + np.random.normal(0, 50000, 100)  # Price
distance_from_train = np.random.uniform(0.5, 5, 100)  # Distance from train in miles
distance_from_ocean = np.random.uniform(0.1, 10, 100)  # Distance from ocean in miles
df = pd.DataFrame({
    'Size of House': size_of_house,
    'Price': price,
    'Distance from Train': distance_from_train,
    'Distance from Ocean': distance_from_ocean
})
# Sample 10 points for a less cluttered plot
sampled_df = df.sample(10)
# Adding the inset 
# Filtering sampled data for the inset plot
#inset_data = sampled_df[(sampled_df['Size of House'] >= 2000) & (sampled_df['Size of House'] <= 3000) & (sampled_df['Price'] >= 250000) & (sampled_df['Price'] <= 600000)]
inset_data=sampled_df
inset_ax = ax.inset_axes([0.7, 0.05, 0.25, 0.25])  # Inset axes 
# Scatter plot in the inset with filtered sampled data
sns.scatterplot(data=inset_data, x='Size of House', y='Price', ax=inset_ax, size='Distance from Train', sizes=(40, 200), hue='Distance from Ocean', alpha=0.7, marker='D', legend=False)
# Capturing the part of the original regression line that falls within the bounds
sns.regplot(
    x='Size of House', 
    y='Price', 
    data=df,  # Using the entire dataset for the trend line
    scatter=False, 
    color='red', 
    ax=inset_ax, 
    lowess=True,
    truncate=True  # Truncating the line within the limits of the inset axes
)
# Adjusting the limits of the inset axes
inset_ax.set_xlim(2000, 3500)
inset_ax.set_ylim(600000, 1000000)
# Display the plot
plt.show()

from wordcloud import WordCloud
import matplotlib.pyplot as plt

# Sample from the reviews of a book
reviews = """
????寶藏級???? 原創(chuàng)公眾號『數(shù)據(jù)STUDIO』內(nèi)容超級硬核。公眾號以Python為核心語言，垂直于數(shù)據(jù)科學領(lǐng)域，包括可戳?? Python｜MySQL｜數(shù)據(jù)分析｜數(shù)據(jù)可視化｜機器學習與數(shù)據(jù)挖掘｜爬蟲 等，從入門到進階！
"""
font_path="/System/Library/fonts/PingFang.ttc" #解決中文亂碼

wordcloud = WordCloud(width=800, height=400, background_color='white', font_path=font_path).generate(reviews)
plt.figure(figsize=(12, 7), dpi=150)
plt.imshow(wordcloud, interpolatinotallow='bilinear')
plt.axis('off')  
plt.show()
plt.figure(figsize=(12, 7))
plt.imshow(wordcloud, interpolatinotallow='bilinear')
plt.axis('off')  
plt.show()

import matplotlib.pyplot as plt
import numpy as np
categories = ['Taste', 'Nutritional value', 'Appearance', 'Money Value']
old_values = [3, 4, 4, 3]
new_values = [5, 5, 4, 5]
N = len(categories)
angles = np.linspace(0, 2 * np.pi, N, endpoint=False).tolist()
old_values = np.append(old_values, old_values[0])
new_values = np.append(new_values, new_values[0])
angles = np.append(angles, angles[0])
fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))
ax.fill(angles, old_values, color='blue', alpha=0.4)
ax.fill(angles, product_values, color='lime', alpha=0.4)
ax.set_yticklabels([])
ax.set_xticks(angles[:-1])
ax.set_xticklabels(categories)
plt.title('Benchmarking: Standard vs New Product', size=20)
plt.legend(['Old Product', 'New Product'], loc='lower right', bbox_to_anchor=(1.1, 1.1))
plt.show()

import matplotlib.pyplot as plt
import pandas as pd
from joypy import joyplot
import numpy as np
import scipy.stats as stats
book_festivals = {
    'Mystery': [1,1], 
    'Adventure fiction':[6,2],
    'Fantasy': [11,3],
    'Self-help':[10,2],
    'Sci-Fi': [7,2],
    'Historical fiction': [12,1]
}
genre_data = {}
for genre, params in book_festivals.items():
    mu,sigma=params
    data = np.random.normal(mu, sigma, 300)
    genre_data[genre] = data
genre_data_dict = {genre: data.tolist() for genre, data in genre_data.items()}
data=pd.DataFrame(genre_data_dict)
# Now we can plot it using joyplot
fig, axes = joyplot(
    data,
    figsize=(30, 18),
    colormap=plt.cm.plasma,
    alpha=1.0
)
colors = plt.cm.plasma(np.linspace(0, 1, len(data.columns)))
# Set x-axis labels and limits
axes[-1].set_xlim(1, 12)
month_order = ['January', 'February', 'March', 'April', 'May', 'June',
               'July', 'August', 'September', 'October', 'November', 'December']
axes[-1].set_xticks(range(1, 13))
axes[-1].set_xticklabels(month_order)
axes[-1].tick_params(axis='x', labelsize='30')
axes[-1].set_xticklabels(month_order)
for ax in axes:
    ax.set_yticks([])
    
legend_handles = [plt.Line2D([0], [0], color=color, lw=6, label=genre) for genre, \
                  color in zip(book_festivals.keys(), colors)]
ax.legend(handles=legend_handles, title='Book Genres', loc='upper right', fnotallow='26')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
np.random.seed(0)
ages = np.random.randint(18, 61, 20)  # Random ages between 18 and 60 for 20 customers
purchase_amounts = np.random.randint(200, 1001, 20)  # Random purchase amounts between 200 and 1000 for 20 customers
plt.figure(figsize=(10, 6))
plt.hist2d(ages, purchase_amounts, bins=[5, 5], range=[[18, 60], [200, 1000]], cmap='plasma')
plt.colorbar(label='Number of Customers')
plt.xlabel('Age')
plt.ylabel('Purchase Amount ($)')
plt.title('2D Histogram of Customer Age and Purchase Amount')

import matplotlib.pyplot as plt
import numpy as np
years = np.arange(1990, 2011)
biology_students = np.linspace(100, 1000, len(years))
astronomy_students = np.linspace(50, 150, len(years))
math_students = np.linspace(80, 500, len(years))
physics_students = np.linspace(70, 480, len(years))

plt.figure(figsize=(10, 6))
plt.stackplot(years, biology_students, astronomy_students, math_students,\
              physics_students, labels=['Biology', 'Astronomy', 'Math', 'Physics'],\
              colors=['#76b947', '#fcb001', '#00a2e8', '#ff7f27'])
plt.legend(loc='upper left')
plt.title('University Department Student Numbers (1990-2010)')
plt.xlabel('Year')
plt.ylabel('Number of Students')
plt.tight_layout()

plt.show()

import matplotlib.pyplot as plt
import numpy as np
years = np.arange(2010, 2021)
revenue = np.linspace(10, 60, len(years))  
marketing_costs = revenue * 0.4  

plt.figure(figsize=(8, 6))
plt.bar(years, revenue, color='lightblue', label='Revenue')
plt.plot(years, marketing_costs, color='red', marker='o', \
linestyle='-', linewidth=2, markersize=6, label='Marketing Costs')
plt.xlabel('Year')
plt.ylabel('Revenue (Millions)')
plt.title('Bar and Line Combination Plot')
plt.legend()
plt.tight_layout()
plt.show()

plt.figure(figsize=(8, 6))
plt.stackplot(years, marketing_costs, revenue, labels=['Marketing Costs', 'Revenue'], colors=['lightcoral', 'palegreen'])
plt.xlabel('Year')
plt.ylabel('Total Amount (Millions)')
plt.title('Area Plot')
plt.legend()
plt.tight_layout()
plt.show()