在 FIFA 20 将技能相似球员进行分组（2）：层次聚类

import pandas as pdimport numpy as npdf = pd.read_csv("/content/players_20.csv")df = df[['short_name','age', 'height_cm', 'weight_kg', 'overall', 'potential','value_eur', 'wage_eur', 'international_reputation', 'weak_foot','skill_moves', 'release_clause_eur', 'team_jersey_number','contract_valid_until', 'nation_jersey_number', 'pace', 'shooting','passing', 'dribbling', 'defending', 'physic', 'gk_diving','gk_handling', 'gk_kicking', 'gk_reflexes', 'gk_speed','gk_positioning', 'attacking_crossing', 'attacking_finishing','attacking_heading_accuracy', 'attacking_short_passing','attacking_volleys', 'skill_dribbling', 'skill_curve','skill_fk_accuracy', 'skill_long_passing', 'skill_ball_control','movement_acceleration', 'movement_sprint_speed', 'movement_agility','movement_reactions', 'movement_balance', 'power_shot_power','power_jumping', 'power_stamina', 'power_strength', 'power_long_shots','mentality_aggression', 'mentality_interceptions','mentality_positioning', 'mentality_vision', 'mentality_penalties','mentality_composure', 'defending_marking', 'defending_standing_tackle','defending_sliding_tackle','goalkeeping_diving','goalkeeping_handling', 'goalkeeping_kicking','goalkeeping_positioning', 'goalkeeping_reflexes']]df = df[df.overall > 86] # extracting players with overall above 86df = df.fillna(df.mean())names = df.short_name.tolist() # saving names for laterdf = df.drop(['short_name'], axis = 1) # drop the short_name columndf.head()

from sklearn import preprocessingx = df.values # numpy arrayscaler = preprocessing.MinMaxScaler()x_scaled = scaler.fit_transform(x)X_norm = pd.DataFrame(x_scaled)

import matplotlib.pyplot as pltimport scipy.cluster.hierarchy as sch# plot dendrogram using average linkageplt.figure(figsize=(10,14))plt.title('Hierarchical Clustering Dendrogram with Average Linkage')dendrogram = sch.dendrogram(sch.linkage(X_norm, method="average"), labels= names, leaf_font_size = 13, orientation='right')

# plot dendrogram using single linkageplt.figure(figsize=(10,14))plt.title('Hierarchical Clustering Dendrogram with Single Linkage')dendrogram = sch.dendrogram(sch.linkage(X_norm, method="single"), labels= names, leaf_font_size = 13, orientation='right')

# plot dendrogram using centroid linkageplt.figure(figsize=(10,14))plt.title('Hierarchical Clustering Dendrogram with Centroid Linkage')dendrogram = sch.dendrogram(sch.linkage(X_norm, method="centroid"), labels= names, leaf_font_size = 13, orientation='right')

# plot dendrogram using complete linkageplt.figure(figsize=(10,14))plt.title('Hierarchical Clustering Dendrogram with Complete Linkage')dendrogram = sch.dendrogram(sch.linkage(X_norm, method="complete"), labels= names, leaf_font_size = 13, orientation='right')