import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split # 数据分析 df = pd.read_csv('iris.csv', skiprows=[0], names=['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'class']) print(df.info()) print(df.describe()) print(df.isnull().sum()) # 随机抽取数据 train_data, test_data = train_test_split(df, test_size=0.3) train_data.to_csv('train_data.csv', index=False) test_data.to_csv('test_data.csv', index=False) # 数据可视化 df.plot(x='class', y=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], kind='line', title='Line Plot', figsize=(10, 5)) df.hist(bins=10, figsize=(10, 5)) df.plot(x='petal_length', y='petal_width', kind='scatter', title='Scatter Plot', figsize=(10, 5)) plt.show() 对上面每一行代码注释

pd_split_train_test.rar_pandas_pandas对数据分类_pd.split_split_数据分类

使用pandas对数据分类,对训练集测试集进行分类

详解pandas库pd.read_excel操作读取excel文件参数整理与实例

主要介绍了pandas库pd.read_excel操作读取excel文件参数整理与实例，小编觉得挺不错的，现在分享给大家，也给大家做个参考。一起跟随小编过来看看吧

import pandas as pd.docx

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt import pandas as pd from sklearn.utils import shuffle from sklearn.preprocessing import scale df = pd.read_csv("C:\\boston.csv",header=0) ds = df.values from sklearn.datasets import load_boston boston = load_boston() X = boston.data y = boston.target from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense model = Sequential([ Dense(64, activation='relu', input_shape=(X_train.shape[1],)), Dense(64, activation='relu'), Dense(64, activation='relu'), Dense(1) ]) model.compile(loss='mean_squared_error', optimizer='adam') history = model.fit(X_train, y_train, validation_split=0.1, epochs=100, batch_size=32) from sklearn.metrics import mean_squared_error y_pred = model.predict(x_test)mse = mean_squared_error(y_test, y_pred)print('MSE:’, mse) import matplotlib.pyplot as plt plt.plot(history.history['accuracy'], label='train') plt.plot(history.history['val_accuracy'], label='validation') plt.legend() plt.show()

from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) 对训练集和测试集进行标准化处理： from sklearn....

import matplotlib.pyplot as plt import pandas as pd df = pd.read_excel(r"db聚类专用版.xlsx") df.head() from sklearn.model_selection import train_test_split #数据划分 X = df[["Bridge length (m)","Structural type","Pier type","Foundation type", "Bearing type","Plane linear"]] y = df[['Vulnerability grade']] xtrain, xtest, ytrain, ytest =\ train_test_split(X, y, test_size=0.2, random_state=100) from sklearn.ensemble import RandomForestClassifier rf = RandomForestClassifier( n_estimators=100, random_state=8 ) rf.fit(xtrain, ytrain) #预测训练集结果 train_predicted = rf.predict(xtrain)

这段代码使用了 matplotlib.pyplot 和 pandas 库，并读取了一个名为 "db聚类专用版.xlsx" 的 Excel 文件。接下来，使用 pandas 的 read_excel() 函数将 Excel 文件读取为一个名为 df 的 DataFrame 对象...

import numpy as np import pandas as pd import matplotlib. pyplot as plt from sklearn.datasets import load_boston from sklearn.model_selection import train_test_split from linear_model_03.closed_form_sol.LinearRegression_CFSol import LinearRegressionClosedFormSol # 数据2，读取数据，先进行数据转换 df = pd.read_table('../data/mpg.data', header=0) # data换成txt,即可转化txt格式 df.to_csv('../data/mpg.csv', index=False) mpg = pd. read_csv("../data/mpg.csv"). dropna() # ..表示上两级目录 X, y = np. asarray(mpg. loc[:, "horsepower"]), np. asarray(mpg. loc[:, "displacement"]) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0, shuffle=True) lr_cfs = LinearRegressionClosedFormSol(fit_intercept=True, normalized=True) # 默认训练偏置项和进行标准化 lr_cfs.fit(X_train, y_train) # 训练模型 theta = lr_cfs.get_params() print(theta) y_test_pred = lr_cfs.predict(x_test=X_test) mse, r2, r2c = lr_cfs.cal_mse_r2(y_test, y_test_pred) print("均方误差：%.5f,判决系数：%.5f,修正判决系数：%.5f" % (mse, r2, r2c)) # lr_cfs. plt_predict(y_test, y_test_pred, is_sort=False) lr_cfs.plt_predict(y_test, y_test_pred, is_sort=True) plt. figure(figsize=(7,5)) plt. plot(X_test, y_test, "ro", label="Test Samples") plt. plot(X_test, y_test_pred, "k-", lw=1.5, label="Fit Model") plt. legend(frameon=False) plt. show()

from sklearn.model_selection import train_test_split from linear_model_03.closed_form_sol.LinearRegression_CFSol import LinearRegressionClosedFormSol # 数据2，读取数据，先进行数据转换 df = pd.read_...

import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split # 读取数据 df = pd.read_csv('./二手房.csv',encoding='gbk') df.head(10)# 取出房屋面积和房龄作为特征 X = df[['Square','house age']].values # 取出房价作为标签 y = df['price'].values # 将数据集拆分为训练集和测试集 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)from sklearn.linear_model import LinearRegression # 创建线性回归模型 lr = LinearRegression() # 训练模型 lr.fit(X_train, y_train) # 在测试集上进行预测 y_pred = lr.predict(X_test)plt.scatter(X_train[:, 0], y_train, color='blue', label='Training set') plt.scatter(X_test[:, 0], y_test, color='green', label='Test set') # 绘制模型预测结果 plt.plot(X_test[:, 0], y_pred, color='red', label='Prediction') plt.title('House Prices Prediction') plt.xlabel('Square') plt.ylabel('price') plt.legend(loc='upper left') plt.show()拟合曲线不是一条直线如何修改代码

from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn.preprocessing import PolynomialFeatures # 读取数据 df = pd.read_csv('./二手房....

import seaborn as sns import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression df = pd.read_csv('heart.csv') corrmat = df.corr() top_corr_features = corrmat.index plt.figure(figsize=(16,16)) sns.heatmap(df[top_corr_features].corr(),annot=True,cmap="RdYlGn") plt.show() sns.set_style('whitegrid') sns.countplot(x='target',data=df,palette='RdBu_r') plt.show() dataset = pd.get_dummies(df, columns=['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal']) columns_to_scale = ['age', 'trestbps', 'chol', 'thalach', 'oldpeak'] scaler = StandardScaler() dataset[columns_to_scale] = scaler.fit_transform(dataset[columns_to_scale]) dataset.head() y = dataset['target'] X = dataset.drop(['target'], axis=1) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0) logreg = LogisticRegression() logreg.fit(X_train, y_train) print("Training accuracy: {:.3f}".format(logreg.score(X_train, y_train))) print("Test accuracy: {:.3f}".format(logreg.score(X_test, y_test)))改写为ROC代码

from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression from sklearn.metrics import roc_curve, auc df...

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier # 导入需要的模块 import warnings warnings.filterwarnings("ignore") from sklearn.metrics import confusion_matrix from itertools import cycle # from scipy import interp from sklearn.metrics import roc_curve, auc data = pd.read_csv('newdate.csv') print(data.head()) print(data.info()) print(data[data['Label'].isnull()]) data = data.dropna() print(data.info()) data['Label'] = data['Label'].map(int) print(data.info()) # 数据归一化 def normalization(data): _range = np.max(data) - np.min(data) return (data - np.min(data)) / _range data['铁水温度'] = normalization(data['铁水温度']) data['透气性指数'] = normalization(data['透气性指数']) print(data) # 相关性分析 plt.figure(figsize=(10, 10)) sns.heatmap(data=data.corr(), annot=True, cmap='Accent', vmax=1, vmin=-1) plt.show() df = pd.DataFrame(data.groupby(['Label'])['铁水温度'].count()) df.columns = ['num'] df.reset_index(inplace=True) print(df)解释每一行代码

from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier from sklearn.tree import DecisionTreeClassifier import warnings warnings.filterwarnings(...

import pandas as pd import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import confusion_matrix, classification_report, accuracy_score # 1. 数据准备 train_data = pd.read_csv('train.csv') test_data = pd.read_csv('test_noLabel.csv') # 填充缺失值 train_data.fillna(train_data.mean(), inplace=True) test_data.fillna(test_data.mean(), inplace=True) # 2. 特征工程 X_train = train_data.drop(['Label', 'ID'], axis=1) y_train = train_data['Label'] X_test = test_data.drop('ID', axis=1) scaler = StandardScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) # 3. 模型建立 model = RandomForestClassifier(n_estimators=100, random_state=42) # 4. 模型训练 model.fit(X_train, y_train) # 5. 进行预测 y_pred = model.predict(X_test) # 6. 保存预测结果 df_result = pd.DataFrame({'ID': test_data['ID'], 'Label': y_pred}) df_result.to_csv('forecast_result.csv', index=False) # 7. 模型评估 y_train_pred = model.predict(X_train) print('训练集准确率：', accuracy_score(y_train, y_train_pred)) print('测试集准确率：', accuracy_score(y_test, y_pred)) print(classification_report(y_test, y_pred)) # 8. 绘制柱形图 feature_importances = pd.Series(model.feature_importances_, index=X_train.columns) feature_importances = feature_importances.sort_values(ascending=False) plt.figure(figsize=(10, 6)) sns.barplot(x=feature_importances, y=feature_importances.index) plt.xlabel('Feature Importance Score') plt.ylabel('Features') plt.title('Visualizing Important Features') plt.show() # 9. 对比类分析 train_data['Label'].value_counts().plot(kind='bar', color=['blue', 'red']) plt.title('Class Distribution') plt.xlabel('Class') plt.ylabel('Frequency') plt.show()

这段代码是一个机器学习模型的完整流程，包括数据准备、特征工程、模型建立、模型训练、预测结果保存、模型评估和可视化分析等步骤。其中包括了绘制柱形图和对比类分析的代码。绘制柱形图的代码如下： ...

# 导入需要的库import pandas as pdfrom sklearn.model_selection import train_test_splitfrom sklearn.svm import SVCfrom sklearn.metrics import accuracy_score, confusion_matrix# 读取 Excel 表格数据df = pd.read_excel('data.xlsx')# 分离特征变量和因变量X = df.iloc[:, :-1]y = df.iloc[:, -1]# 将数据分为训练集和验证集X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)# 训练支持向量机模型svm = SVC(kernel='linear')svm.fit(X_train, y_train)# 预测新的数据new_data = pd.read_excel('new_data.xlsx')y_pred = svm.predict(new_data)# 输出预测结果到 Excel 表格new_data['Prediction'] = y_prednew_data.to_excel('predictions.xlsx', index=False)# 输出模型精度和混淆矩阵print('Accuracy:', accuracy_score(y_test, svm.predict(X_test)))print('Confusion Matrix:', confusion_matrix(y_test, svm.predict(X_test)))输出混淆矩阵图片

import matplotlib.pyplot as plt import seaborn as sns import pandas as pd from sklearn.metrics import confusion_matrix # 读取 Excel 表格数据 df = pd.read_excel('data.xlsx') # 分离特征变量和因变量 X ...

#根据编程要求，补充下面Begin-End区间的代码 import numpy as np import pandas as pd import numpy as np import pandas as pd from sklearn.tree import DecisionTreeClassifier, export_graphviz # 导入决策树模型 from sklearn.model_selection import train_test_split # 导入数据集划分模块 import matplotlib.pyplot as plt from sklearn.metrics import roc_auc_score from sklearn.metrics import classification_report # 数据的读入与处理 data_path ='/data/bigfiles/7db918ff-d514-49ea-8f6b-ea968df742e9' df = pd.read_csv(data_path,header=None,names=['age', 'workclass', 'fnlwgt', 'education', 'education-num','marital-status','occupation','relationship','race','sex','capital-gain','capital-loss','hours-per-week','native-country','salary']) ######Begin ###### # 去除字符串数值前面的空格 # 去除fnlwgt, capital-gain, capital-loss,特征属性 # 将特征采用哑变量进行编码，字符型特征经过转化可以进行训练 # 将label编码 ###### End ###### ######Begin ###### # 按4：1的比例划分训练和测试集 # 构建模型 #对训练集X_train训练 #对于测试集x_test进行预测 # 其他指标计算 print(classification_report(y_test, x_pre_test)) # 预测测试集概率值 #计算验证集的auc值,参数为预测值和概率估计 ###### End ###### print("auc的值：{}".format(auc))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 构建模型 dt = DecisionTreeClassifier(random_state=42) # 对训练集X_train训练 dt.fit(X_train, y_train) # ...

from sklearn import metrics from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from imblearn.combine import SMOTETomek from sklearn.metrics import auc, roc_curve, roc_auc_score from sklearn.feature_selection import SelectFromModel import pandas as pd import numpy as np import matplotlib matplotlib.use('TkAgg') import matplotlib.pyplot as plt from sklearn.metrics import confusion_matrix #1、数据输入 df_table_all = pd.read_csv(r"D:\trainafter.csv",index_col=0) #2、目标和特征区分 X = df_table_all.drop(["Y"],axis=1).values Y = np.array(df_table_all["Y"]) #3、按比例切割数据 X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.3,random_state=0) #4、样本平衡， st= SMOTETomek() X_train_st,Y_train_st = st.fit_resample(X_train,Y_train) #4、特征选择： #创建特征选择模型 sfm = SelectFromModel(LogisticRegression(penalty='l1',C=1.0,solver="liblinear")) #训练特征选择模型 sfm.fit(X_train,Y_train) #讲数据转换，剩下重要的特征 X_train_tiny = sfm.transform(X_train) X_test_tiny = sfm.transform(X_test) #5、创建模型 model = LogisticRegression(penalty='l1',C=1.0,solver="liblinear") model.fit(X_train_st_tiny,Y_train_st) #6、预测 y_pred = model.predict_proba(X_test_st_tiny) y_cate = model.predict(X_test_st_tiny) c=confusion_matrix(Y_test,y_cate) print(c) def report_auc(y_true,y_prob,title,out_name="",lw=2): fpr,tpr,_=roc_curve(y_true,y_prob,pos_label=1) print(fpr) print(tpr) plt.figure() plt.plot(fpr,tpr,color="darkorange",lw=lw,lable="ROC curve") plt.plot([0,1],[0,1],color="yellow",lw=lw,linestyle="--") plt.xlim([0,1]) plt.ylim([0,1.05]) plt.title(title) plt.legend(loc='lower right') plt.show(0) plt.savefig(r"d:\LR"+out_name,dpi=800) plt.close("all") report_auc(Y_test,y_pred[:,1],"Logistic with L1 panetly",'LG')

SMOTETomek是用于处理样本不平衡问题的，auc、roc_curve、roc_auc_score是用于评估分类模型性能的指标，train_test_split是用于将数据集分为训练集和测试集的，SelectFromModel是用于特征选择的。同时，还使用了...

# 导入相关库 import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeClassifier from sklearn.ensemble import RandomForestClassifier from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score,roc_auc_score,roc_curve # 读取数据 df = pd.read_csv('C:/Users/E15/Desktop/机器学习作业/第一次作业/第一次作业/三个数据集/Titanic泰坦尼克号.csv') # 数据预处理 df = df.drop(["Name", "Ticket", "Cabin"], axis=1) # 删除无用特征 df = pd.get_dummies(df, columns=["Sex", "Embarked"]) # 将分类特征转换成独热编码 df = df.fillna(df.mean()) # 使用平均值填充缺失值 # 划分数据集 X = df.drop(["Survived"], axis=1) y = df["Survived"] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # 决策树 dtc = DecisionTreeClassifier(random_state=42) dtc.fit(X_train, y_train) y_pred_dtc = dtc.predict(X_test) # 剪枝决策树 pruned_dtc = DecisionTreeClassifier(random_state=42, ccp_alpha=0.015) pruned_dtc.fit(X_train, y_train) y_pred_pruned_dtc = pruned_dtc.predict(X_test) # 随机森林 rfc = RandomForestClassifier(n_estimators=100, random_state=42) rfc.fit(X_train, y_train) y_pred_rfc = rfc.predict(X_test) # 计算评价指标 metrics = {"Accuracy": accuracy_score, "Precision": precision_score, "Recall": recall_score, "F1-Score": f1_score, "AUC": roc_auc_score} results = {} for key in metrics.keys(): if key == "AUC": results[key] = {"Decision Tree": roc_auc_score(y_test, y_pred_dtc), "Pruned Decision Tree": roc_auc_score(y_test, y_pred_pruned_dtc), "Random Forest": roc_auc_score(y_test, y_pred_rfc)} else: results[key] = {"Decision Tree": metrics[key](y_test, y_pred_dtc), "Pruned Decision Tree": metrics[key](y_test, y_pred_pruned_dtc), "Random Forest": metrics[key](y_test, y_pred_rfc)} # 打印评价指标的表格 results_df = pd.DataFrame(results) print(results_df)怎么打印auv图

要打印AUC图，可以使用roc_curve函数获取ROC曲线的参数，然后使用matplotlib库绘制曲线。具体代码如下： # 计算ROC曲线参数 fpr_dtc, tpr_dtc, thresholds_dtc = roc_curve(y_test, y_pred_dtc) fpr_pruned...

import pandas as pd import matplotlib import numpy as np import matplotlib.pyplot as plt import jieba as jb import re from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.feature_selection import chi2 import numpy as np from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import CountVectorizer from sklearn.feature_extraction.text import TfidfTransformer from sklearn.naive_bayes import MultinomialNB def sigmoid(x): return 1 / (1 + np.exp(-x)) import numpy as np #定义删除除字母,数字，汉字以外的所有符号的函数 def remove_punctuation(line): line = str(line) if line.strip()=='': return '' rule = re.compile(u"[^a-zA-Z0-9\u4E00-\u9FA5]") line = rule.sub('',line) return line def stopwordslist(filepath): stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()] return stopwords df = pd.read_csv('./online_shopping_10_cats/online_shopping_10_cats.csv') df=df[['cat','review']] df = df[pd.notnull(df['review'])] d = {'cat':df['cat'].value_counts().index, 'count': df['cat'].value_counts()} df_cat = pd.DataFrame(data=d).reset_index(drop=True) df['cat_id'] = df['cat'].factorize()[0] cat_id_df = df[['cat', 'cat_id']].drop_duplicates().sort_values('cat_id').reset_index(drop=True) cat_to_id = dict(cat_id_df.values) id_to_cat = dict(cat_id_df[['cat_id', 'cat']].values) #加载停用词 stopwords = stopwordslist("./online_shopping_10_cats/chineseStopWords.txt") #删除除字母,数字，汉字以外的所有符号 df['clean_review'] = df['review'].apply(remove_punctuation) #分词，并过滤停用词 df['cut_review'] = df['clean_review'].apply(lambda x: " ".join([w for w in list(jb.cut(x)) if w not in stopwords])) tfidf = TfidfVectorizer(norm='l2', ngram_range=(1, 2)) features = tfidf.fit_transform(df.cut_review) labels = df.cat_id X_train, X_test, y_train, y_test = train_test_split(df['cut_review'], df['cat_id'], random_state = 0) count_vect = CountVectorizer() X_train_counts = count_vect.fit_transform(X_train) tfidf_transformer = TfidfTransformer() X_train_tfidf = tfidf_transformer.fit_transform(X_train_counts) 已经写好以上代码，请补全train和test函数

以下是train和test函数的代码： python def train(X_train_tfidf, y_train): clf = MultinomialNB().fit(X_train_tfidf, y_train) return clf def test(clf, X_test): X_test_counts = count_vect.transform...

import streamlit as st import numpy as np import pandas as pd import pickle import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_selection import train_test_split from sklearn.decomposition import PCA from sklearn.svm import SVC from sklearn.neighbors import KNeighborsClassifier from sklearn.ensemble import RandomForestClassifier import streamlit_echarts as st_echarts from sklearn.metrics import accuracy_score,confusion_matrix,f1_score def pivot_bar(data): option = { "xAxis":{ "type":"category", "data":data.index.tolist() }, "legend":{}, "yAxis":{ "type":"value" }, "series":[ ] }; for i in data.columns: option["series"].append({"data":data[i].tolist(),"name":i,"type":"bar"}) return option st.markdown("mode pracitce") st.sidebar.markdown("mode pracitce") df=pd.read_csv(r"D:\课程数据\old.csv") st.table(df.head()) with st.form("form"): index_val = st.multiselect("choose index",df.columns,["Response"]) agg_fuc = st.selectbox("choose a way",[np.mean,len,np.sum]) submitted1 = st.form_submit_button("Submit") if submitted1: z=df.pivot_table(index=index_val,aggfunc = agg_fuc) st.table(z) st_echarts(pivot_bar(z)) df_copy = df.copy() df_copy.drop(axis=1,columns="Name",inplace=True) df_copy["Response"]=df_copy["Response"].map({"no":0,"yes":1}) df_copy=pd.get_dummies(df_copy,columns=["Gender","Area","Email","Mobile"]) st.table(df_copy.head()) y=df_copy["Response"].values x=df_copy.drop(axis=1,columns="Response").values X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2) with st.form("my_form"): estimators0 = st.slider("estimators",0,100,10) max_depth0 = st.slider("max_depth",1,10,2) submitted = st.form_submit_button("Submit") if "model" not in st.session_state: st.session_state.model = RandomForestClassifier(n_estimators=estimators0,max_depth=max_depth0, random_state=1234) st.session_state.model.fit(X_train, y_train) y_pred = st.session_state.model.predict(X_test) st.table(confusion_matrix(y_test, y_pred)) st.write(f1_score(y_test, y_pred)) if st.button("save model"): pkl_filename = "D:\\pickle_model.pkl" with open(pkl_filename, 'wb') as file: pickle.dump(st.session_state.model, file) 会出什么错误

1. 你需要保证数据集的路径正确，并且数据集的格式正确。 2. 如果使用了 streamlit_echarts 库，在运行代码前需要先安装该库，可以通过 !pip install streamlit_echarts 命令进行安装。 3. 确保所有的依赖项都...

import numpy as np import pandas as pd import matplotlib.pyplot as plt from decision_tree_classifier import DecisionTreeClassifier from random_forest_classifier import RandomForestClassifier from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score #读取数据 df = pd.read_csv('adult.csv',encoding='gbk') df.head() col_names=['age','workclass','fnlwgt','education','educational-num','marital-status','occupation','relationship','race','gender','capital-gain','capital-loss','hours-per-week','native-country','income'] df.columns = col_names categorical = ['workclass','education','marital-status','occupation','relationship','race','gender','native-country','income'] # print(f'分类特征：\n{categorical}') # for var in categorical: # print(df[var].value_counts()) #缺失值处理 df['occupation'].replace('?', np.NaN, inplace=True) df['workclass'].replace('?', np.NaN, inplace=True) df['native-country'].replace('?', np.NaN, inplace=True) df.isnull().sum() df['income'].value_counts() plt.rcParams['font.sans-serif'] = ['Microsoft YaHei'] df.isnull().sum() df['workclass'].fillna(df['workclass'].mode()[0], inplace=True) df['occupation'].fillna(df['occupation'].mode()[0], inplace=True) df['native-country'].fillna(df['native-country'].mode()[0], inplace=True) df = pd.get_dummies(df,columns=categorical,drop_first=True) print(df.head()) y = df.loc[:,'income_>50K'] X = np.array(df.loc[:,['age', 'educational-num', 'hours-per-week']]) y = np.array(y) x = np.array(X) y = y.reshape(-1,1) X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=1234) from sklearn.ensemble import RandomForestClassifier rtree = RandomForestClassifier(n_estimators=100,max_depth=5,max_features=0.2,max_samples=50,random_state=1234) X_train = np.array(X_train) rtree.fit(X_train, y_train) X_test = np.array(X_test) y_pred = rtree.predict(X_test) accuracy = accuracy_score(y_test,y_pred) print("accuracy={}".format((accuracy)))我这个代码如何更换特征向量

X = np.array(df.loc[:,['age', 'educational-num', 'hours-per-week']]) y = np.array(y) 将 ['age', 'educational-num', 'hours-per-week'] 替换为你想要的特征向量即可。注意要保证特征向量的格式正确，即...

import pandas as pd from sklearn import metrics from sklearn.model_selection import train_test_split import xgboost as xgb import matplotlib.pyplot as plt import openpyxl # 导入数据集 df = pd.read_csv("/Users/mengzihan/Desktop/正式有血糖聚类前.csv") data=df.iloc[:,:35] target=df.iloc[:,-1] # 切分训练集和测试集 train_x, test_x, train_y, test_y = train_test_split(data,target,test_size=0.2,random_state=7) # xgboost模型初始化设置 dtrain=xgb.DMatrix(train_x,label=train_y) dtest=xgb.DMatrix(test_x) watchlist = [(dtrain,'train')] # booster: params={'booster':'gbtree', 'objective': 'binary:logistic', 'eval_metric': 'auc', 'max_depth':12, 'lambda':10, 'subsample':0.75, 'colsample_bytree':0.75, 'min_child_weight':2, 'eta': 0.025, 'seed':0, 'nthread':8, 'gamma':0.15, 'learning_rate' : 0.01} # 建模与预测：50棵树 bst=xgb.train(params,dtrain,num_boost_round=50,evals=watchlist) ypred=bst.predict(dtest) # 设置阈值、评价指标 y_pred = (ypred >= 0.5)*1 print ('Precesion: %.4f' %metrics.precision_score(test_y,y_pred)) print ('Recall: %.4f' % metrics.recall_score(test_y,y_pred)) print ('F1-score: %.4f' %metrics.f1_score(test_y,y_pred)) print ('Accuracy: %.4f' % metrics.accuracy_score(test_y,y_pred)) print ('AUC: %.4f' % metrics.roc_auc_score(test_y,ypred)) ypred = bst.predict(dtest) print("测试集每个样本的得分\n",ypred) ypred_leaf = bst.predict(dtest, pred_leaf=True) print("测试集每棵树所属的节点数\n",ypred_leaf) ypred_contribs = bst.predict(dtest, pred_contribs=True) print("特征的重要性\n",ypred_contribs ) xgb.plot_importance(bst,height=0.8,title='影响糖尿病的重要特征', ylabel='特征') plt.rc('font', family='Arial Unicode MS', size=14) plt.show()

1. 导入必要的库：pandas用于数据处理，sklearn中的metrics模块用于评价指标，train_test_split用于划分训练集和测试集，xgboost用于建模，matplotlib.pyplot用于画图，openpyxl用于读取Excel文件。...

pandas.read_csv参数详解(小结)

主要介绍了pandas.read_csv参数详解(小结)，文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值，需要的朋友们下面随着小编来一起学习学习吧

相关推荐

pd_split_train_test.rar_pandas_pandas对数据分类_pd.split_split_数据分类

详解pandas库pd.read_excel操作读取excel文件参数整理与实例

import pandas as pd.docx

pandas.read_csv参数详解(小结)

最新推荐

node-v4.8.6-win-x64.zip

基础运维技能（下）md格式笔记

zigbee-cluster-library-specification

管理建模和仿真的文件

实现实时数据湖架构：Kafka与Hive集成

如何用python编写api接口

JSBSim Reference Manual

"互动学习：行动中的多样性与论文攻读经历"

实现实时监控告警系统：Kafka与Grafana整合

matlab 将加载的数据转变为矩阵