蚂蚁暑期 319 笔试

蚂蚁暑期 319 笔试

全相等

解题：

defsolve():n=int(input())s=input()ans=0forleftinrange(n):freq=[0]*26forrightinrange(left,n):freq[ord(s[right])-ord('a')]+=1vals=set(iforiinfreqifi>0)iflen(vals)==1:ans+=1print(ans)T=int(input())for_inrange(T):solve()

文本数值混合特征工程

求解：

机器学习的题目 本质都是数据加载 -> 特征处理 -> 模型训练 -> 预测输出这四个固定模块

importjsonimportnumpyasnpfromsklearn.feature_extraction.textimportTfidfVectorizerfromsklearn.linear_modelimportSGDClassifier,LogisticRegressionfromsklearn.preprocessingimportStandardScaler,PolynomialFeaturesfromscipy.sparseimporthstack# 1. 加载数据data=json.loads(input())train_txt=data['train_txt']train_num=np.array(data['train_num'])train_y=np.array(data['train_y'])test_txt=data['test_txt']test_num=np.array(data['test_num'])# Word-level TF-IDFword_vec=TfidfVectorizer(lowercase=True,stop_words="english",ngram_range=(1,2),sublinear_tf=True)tr_word=word_vec.fit_transform(train_txt)te_word=word_vec.transform(test_txt)# Char 3-gram TF-IDFchar_vec=TfidfVectorizer(analyzer="char",ngram_range=(3,3),lowercase=True,sublinear_tf=True)tr_char=char_vec.fit_transform(train_txt)te_char=char_vec.transform(test_txt)# Numeric: StandardScaler + PolynomialFeaturesscaler=StandardScaler()poly=PolynomialFeatures(degree=2,include_bias=False)tr_num=poly.fit_transform(scaler.fit_transform(train_num))te_num=poly.transform(scaler.fit_transform(test_num))# 合并X_tr=hstack([tr_word,tr_char,tr_num])X_te=hstack([te_word,te_char,te_num])# LogisticRegressionlr=LogisticRegression(penalty='l2',solver='liblinear',max_iter=1000,random_state=42)lr.fit(X_tr,train_y)# SGDClassifiersgd=SGDClassifier(loss='log_loss',penalty='l2',alpha=1e-4,max_iter=1000,random_state=42)sgd.fit(X_tr,train_y)# 软投票prob=(lr.predict_proba(X_te)[:1]+sgd.predict_proba(X_te)[:1])/2preds=(prob>0.5).astype(int).tolist()print(json.dumps(preds))

三元异或

考的是 异或的基本性质：a⊕b=c⟹a=b⊕c,b=a⊕c

defsolve():n,k=map(int,input().split())nums=list(map(int,input().split()))# a_i ^ a_j ^ a_p ^ a_q = k => a_i ^ a_j = k ^ (a_p ^ a_q)mp={}# key为 a_i ^ a_j的值， value是数组，存放 下标元组(i, j)foriinrange(n):forjinrange(i+1,n):v=nums[i]^nums[j]ifvnotinmp:mp[v]=[]mp[v].append((i,j))foriinrange(n):forjinrange(i+1,n):target=nums[i]^nums[j]^kiftargetnotinmp:continuefora,binmp[target]:ifi!=aandi!=bandj!=aandj!=b:print("Yes")returnprint("No")T=int(input())for_inrange(T):solve()