ScriptPython

---------- History of Rugby ----------

import matplotlib as mpt
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
import numpy as np

plt.figure(figsize=(27,7))

sns.lineplot(
    data=dataset,
    x='Año',
    y='Total_Matches',
    linewidth=4,
    hue='hemisferio'
)
sns.regplot(
    data=dataset,
    x='Año',
    y='Total_Matches',
    scatter=False,
    color='black',
    line_kws={'linestyle': '--'}
)

future_years_start = 2025
future_years_end = 2030

years = np.array(dataset['Año']).reshape(-1, 1)
hemisferios = dataset['hemisferio'].unique()

# Haremos una regresión lineal para cada hemisferio
for hemisferio in hemisferios:
    # Filtramos por hemisferio
    hemisferio_data = dataset[dataset['hemisferio'] == hemisferio]
    
    # Creamos el modelo de regresión
    X = np.array(hemisferio_data['Año']).reshape(-1, 1)
    y = np.array(hemisferio_data['Total_Matches'])
    
    # Entrenamos el modelo de regresión lineal
    model = LinearRegression()
    model.fit(X, y)
    
    # Proyección para los años futuros
    last_year = dataset['Año'].max()
    future_years = np.arange(future_years_start, future_years_end + 1).reshape(-1, 1)
    projected_matches = model.predict(future_years)
    
    # Dibujar la proyección
    plt.plot(
        future_years,
        projected_matches,
        linestyle="--",
        linewidth=3,
        color='blue' if hemisferio == 'Norte' else 'green',
        label=f'Proyección {hemisferio}',
    )

plt.axvline(
    x=1871,
    color='#000080',
    linestyle="-",
    linewidth=3
    #label='1871 1º Partido Rugby Internacional'
)
plt.axvline(
    x=1914,
    color='red',
    linestyle="--",
    linewidth=2
    #label='1914 Inicio 1ª Guerra Mundial'
)
plt.axvline(
    x=1918,
    color='red',
    linestyle="--",
    linewidth=2
    #label='1918 Fin 1ª Guerra Mundial'
)
plt.axvline(
    x=1939,
    color='red',
    linestyle="--",
    linewidth=2
    #label='1939 Inicio 2ª Guerra Mundial'
)
plt.axvline(
    x=1945,
    color='red',
    linestyle="--",
    linewidth=2
    #label='1945 Fin 2ª Guerra Mundial'
)
plt.axvline(
    x=1987,
    linestyle="-",
    color='#00845c',
    linewidth=3
    #label='1987 1ª Rugby World Cup'
)
plt.axvline(
    x=1995,
    linestyle="--",
    color='#00845c',
    linewidth=2
    #label='1995 Profesionalizacion del Rugby'
)
plt.axvline(
    x=2012,
    color='#000080',
    linestyle="-",
    linewidth=3
    #label='1996 Rugby Championship'
)

plt.axvline(
    x=2000,
    color='#000080',
    linestyle="-",
    linewidth=3
    #label='2000 Six Nations Championship'
)

plt.axvline(
    x=2020,
    color='red',
    linestyle="--",
    linewidth=2
    #label='2020 Covid 19'
)

plt.xticks(fontsize=18, fontfamily='Segoe UI')
plt.yticks(fontsize=18, fontfamily='Segoe UI')

plt.xlabel(' ')
plt.ylabel('Total Partidos',fontsize=14, fontfamily='DIN')

plt.annotate(
    '1º Partido Rugby Internacional',
    fontsize=18,
    fontfamily='DIN',
    xy=(1871, dataset['Total_Matches'].min()), 
    xytext=(1872, dataset['Total_Matches'].min() + 10),
    arrowprops=dict(facecolor='black', arrowstyle="->")
)

plt.annotate(
    '1ª Guerra Mundial',
    fontsize=18,
    fontfamily='DIN',
    xy=(1915, dataset['Total_Matches'].min()), 
    xytext=(1920, dataset['Total_Matches'].min() + 20),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    '2ª Guerra Mundial',
    fontsize=18,
    fontfamily='DIN', 
    xy=(1943, dataset['Total_Matches'].min()), 
    xytext=(1947, dataset['Total_Matches'].min() + 20),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    '1ª Rugby World Cup',
    fontsize=18,
    fontfamily='DIN', 
    xy=(1987, dataset['Total_Matches'].min()+5), 
    xytext=(1967, dataset['Total_Matches'].min() + 30),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    'Profesionalizacion del Rugby',
    fontsize=18,
    fontfamily='DIN',
    xy=(1995, dataset['Total_Matches'].min()+5), 
    xytext=(1996, dataset['Total_Matches'].min() + 10),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    '1º The Rugby Chapionship (Sur)',
    fontsize=18,
    fontfamily='DIN',
    xy=(2012, dataset['Total_Matches'].min()-5), 
    xytext=(2014, dataset['Total_Matches'].min() + 4),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    '1º Six Nations Championship (Norte)',
    fontsize=18,
    fontfamily='DIN', 
    xy=(2000, dataset['Total_Matches'].min()-5), 
    xytext=(1965, dataset['Total_Matches'].min() ),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.annotate(
    'Covid 19',
    fontsize=18,
    fontfamily='DIN', 
    xy=(2020, dataset['Total_Matches'].min()-5), 
    xytext=(2025, dataset['Total_Matches'].min()-5 ),
    arrowprops=dict(facecolor='red', arrowstyle="->")
)

plt.xticks(range(1870,2031,5),rotation=90)
plt.legend()
plt.tight_layout()

plt.xlim(1865, 2030)
plt.ylim(-8, None) 

plt.show()


---------- Acumulated Points by Hemispherie, Results and Location ----------

import pandas as pd
import matplotlib as mpt
import matplotlib.pyplot as plt

import seaborn as sns

custom_palette = {'Ganador': '#00845c', 'Perdedor': '#d21034'}

dataset = dataset[(dataset['Resultado'] == 'ganador') | (dataset['Resultado'] == 'perdedor')]

dataset['Resultado'] = dataset['Resultado'].replace({'ganador': 'Ganador', 'perdedor': 'Perdedor'})

g = sns.catplot(
    data=dataset,
    x='hemisferio',
    y='score',
    hue='Resultado',
    split=True,
    kind='violin',
    height=5,
    aspect=0.9,
    col='atributo_team_e',
    palette = custom_palette,
)

g.set_xlabels("")
g.set_ylabels("Score", fontsize=11, fontfamily='DIN')

for ax in g.axes.flat:
    ax.tick_params(axis='x', labelsize=11)
    ax.tick_params(axis='y', labelsize=11)

for ax, title in zip(plt.gcf().axes, ['Local', 'Visitante']):
    ax.set_title(title, fontsize=11, fontfamily='Segoe UI')
    
plt.show()


---------- Relationship Between Games Played and Victories ----------

import pandas as pd
import matplotlib as mpt
import matplotlib.pyplot as plt

import seaborn as sns

colores_paises = {
    'Sudafrica': '#1b3838',
    'Nueva Zelanda': 'black',
    'Italia': '#0052b1',
    'Irlanda': '#00845c',
    'Inglaterra': '#808080',
    'Gales': '#d21034',
    'Francia': '#003b7c',
    'Escocia': '#000080',
    'Australia': '#ffbb00',
    'Argentina': '#43A1D5'
}

g = sns.relplot(
    data=dataset,
    x='Total_Win',
    y='Total_Matches',
    hue='Paises',
    size='Total_Win',
    palette= colores_paises,
    height=6,
    aspect=1.4,
    s = 100,
    sizes=(10, 1200),
)

for text in g._legend.texts:
    text.set_text(text.get_text().replace('Total_Win', 'Victorias'))
    
plt.grid(True, linestyle = ':', linewidth=1)

plt.xlabel('Victorias',fontsize=14, fontfamily='DIN')
plt.ylabel('Partidos',fontsize=14, fontfamily='DIN')

plt.xticks(fontsize=11, fontfamily='Segoe UI')
plt.yticks(fontsize=12, fontfamily='Segoe UI')

plt.show()


---------- Distribution of Points by Location ----------

import seaborn as sns
import matplotlib.pyplot as plt

colores_paises = {
    'Sudafrica': '#1b3838',
    'Nueva Zelanda': 'black',
    'Italia': '#0052b1',
    'Irlanda': '#00845c',
    'Inglaterra': '#808080',
    'Gales': '#d21034',
    'Francia': '#003b7c',
    'Escocia': '#000080',
    'Australia': '#ffbb00',
    'Argentina': '#43A1D5'
}

dataset['atributo_team_e'] = dataset['atributo_team_e'].replace({'local': 'Local', 'visitante': 'Visitante'})

g = sns.catplot(
    x='atributo_team_e',
    y='score',
    hue='Paises',
#col='hemisferio',
    data=dataset,
    kind='box',
    height=6.5,
    aspect=1.5,
    palette=colores_paises
)
   
plt.xlabel(' ')
plt.ylabel('Score',fontsize=14, fontfamily='DIN')

plt.xticks(fontsize=12, fontfamily='Segoe UI')
plt.yticks(fontsize=12, fontfamily='Segoe UI')

plt.show()


---------- Distribution of Points by Results ----------

import seaborn as sns
import matplotlib.pyplot as plt

colores_paises = {
    'Sudafrica': '#1b3838',
    'Nueva Zelanda': 'black',
    'Italia': '#0052b1',
    'Irlanda': '#00845c',
    'Inglaterra': '#808080',
    'Gales': '#d21034',
    'Francia': '#003b7c',
    'Escocia': '#000080',
    'Australia': '#ffbb00',
    'Argentina': '#43A1D5'
}

dataset['Resultado'] = dataset['Resultado'].replace({'perdedor': 'Perdedor', 'empate': 'Empate','ganador':'Ganador'})

sns.catplot(
    x='Resultado',
    y='score',
    hue='Paises',
    #col='hemisferio',
    data=dataset,
    kind='box',
    height=6.5,
    aspect=1.5,
    palette= colores_paises
)

plt.xlabel(' ')
plt.ylabel('Score',fontsize=14, fontfamily='DIN')

plt.xticks(fontsize=11, fontfamily='Segoe UI')
plt.yticks(fontsize=12, fontfamily='Segoe UI')

plt.show()


---------- Victories by Age and Country - Main Competitions ----------

import pandas as pd
import matplotlib as mpt
import seaborn as sns
import matplotlib.pyplot as plt

dataset = dataset[(dataset['competition_general'] == 'Six Nations Championship') | (dataset['competition_general'] == 'Rugby Championship') | (dataset['competition_general'] == 'Rugby World Cup')]

dataset = dataset.pivot_table(index='id_pais_union',columns='Año',values='Total_Win',aggfunc='sum')

#plt.figure(figsize=(16,8))
if dataset.empty:
    print("No hay datos para el rango de fechas seleccionado")
else:
    sns.heatmap(
        dataset,
        annot= True,
        annot_kws={"fontsize": 9},
        linewidth=1,
        square=False,
        cbar=True,
        cbar_kws={'orientation': 'horizontal','shrink': 0.9}
    )

plt.xticks(rotation=90,fontsize=12, fontfamily='Segoe UI')
plt.yticks(rotation=360,fontsize=12, fontfamily='Segoe UI')

plt.xlabel('')
plt.ylabel('')

plt.tight_layout(pad=0.5)

plt.show()


---------- Country Rivarly ----------

import pandas as pd
import networkx as nx
import matplotlib.pyplot as plt

colores_paises = {
    'Sudafrica': '#1b3838',
    'Nueva Zelanda': 'black',
    'Italia': '#0052b1',
    'Irlanda': '#00845c',
    'Inglaterra': '#808080',
    'Gales': '#d21034',
    'Francia': '#003b7c',
    'Escocia': '#000080',
    'Australia': '#ffbb00',
    'Argentina': '#43A1D5'
}

# Separar los equipos locales y visitantes
dataset1 = dataset[dataset['id_atributo_team'] == 1][['id_match', 'Paises']].rename(columns={'Paises': 'local'})
dataset2 = dataset[dataset['id_atributo_team'] == 0][['id_match', 'Paises']].rename(columns={'Paises': 'visitante'})

# Unir los datasets por 'id_match'
dataset = pd.merge(dataset1, dataset2, on='id_match')
dataset = dataset.groupby(['local', 'visitante']).size().reset_index(name='frecuencia')
dataset_inverso = dataset[['visitante', 'local', 'frecuencia']].rename(columns={'visitante': 'local', 'local': 'visitante'})

# Combinar el dataset original con el dataset inverso
dataset = pd.concat([dataset, dataset_inverso], axis=0)

# Agrupar nuevamente para sumar la frecuencia de ambas direcciones
dataset = dataset.groupby(['local', 'visitante']).sum().reset_index()

if dataset.empty:
    print("No hay datos para el rango de fechas seleccionado")
else:
    
# Crear el grafo
    G = nx.from_pandas_edgelist(dataset, source ='local', target = 'visitante', edge_attr='frecuencia')

    partidos_por_equipo = dataset.groupby('local')['frecuencia'].sum().to_dict()

# Escalar el tamaño de los nodos de acuerdo al número de partidos
    node_sizes = [partidos_por_equipo.get(node, 1) * 3.5 for node in G.nodes()]

# Crear layout para posicionar los nodos. Aquí utilizamos un layout ajustado por la cantidad de partidos
    pos = nx.spring_layout(G, k=3/len(G.nodes()), iterations=10, scale=2, weight='frecuencia', seed=42)  # Distribuir mejor según el tamaño

# Colores de los nodos
    colors = [colores_paises.get(node, 'white') for node in G.nodes()]

# Dibujar el grafo

    nx.draw(G, pos, with_labels=False, node_color=colors, node_size=node_sizes, edge_color='black', linewidths=2)

# Añadir las etiquetas de los nodos
#nx.draw_networkx_labels(G, pos, font_size=10, font_color='#BAB9B7')

# Crear las etiquetas de las frecuencias en los bordes
    edge_labels = nx.get_edge_attributes(G, 'frecuencia')
    nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8, font_color='red')

# Crear la leyenda personalizada
for node, color in colores_paises.items():
    plt.scatter([], [], c=color, label=node, s=100)

plt.legend(scatterpoints=1, frameon=False, title="Paises",fontsize=8,loc='upper right', borderaxespad=0)

plt.tight_layout()
plt.show()