在 FIFA 20 将技能相似球员进行分组（1）：K- 均值聚类

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 86

df = df.fillna(df.mean())

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

from sklearn.decomposition import PCApca = PCA(n_components = 2) # 2D PCA for the plotreduced = pd.DataFrame(pca.fit_transform(X_norm))

from sklearn.cluster import KMeans# specify the number of clusterskmeans = KMeans(n_clusters=5)# fit the input datakmeans = kmeans.fit(reduced)# get the cluster labelslabels = kmeans.predict(reduced)# centroid valuescentroid = kmeans.cluster_centers_# cluster valuesclusters = kmeans.labels_.tolist()

reduced['cluster'] = clustersreduced['name'] = namesreduced.columns = ['x', 'y', 'cluster', 'name']reduced.head()

import matplotlib.pyplot as pltimport seaborn as sns%matplotlib inlinesns.set(style="white")ax = sns.lmplot(x="x", y="y", hue='cluster', data = reduced, legend=False,fit_reg=False, size = 15, scatter_kws={"s": 250})texts = []for x, y, s in zip(reduced.x, reduced.y, reduced.name):texts.append(plt.text(x, y, s))ax.set(ylim=(-2, 2))plt.tick_params(labelsize=15)plt.xlabel("PC 1", fontsize = 20)plt.ylabel("PC 2", fontsize = 20)plt.show()