工业蒸汽量预测2

1.数据包引入

import matplotlib.pyplot as pltnimport seaborn as snsnimport pandas as pdnimport numpy as npnfrom scipy import statsnfrom sklearn.model_selection import train_test_splitnfrom sklearn.model_selection import GridSearchCV, RepeatedKFoldnfrom sklearn.model_selection import cross_val_score, cross_val_predict, KFoldnfrom sklearn.metrics import make_scorer, mean_squared_errornfrom sklearn.linear_model import LinearRegression, Lasso, Ridge, ElasticNetnfrom sklearn.svm import LinearSVR, SVRnfrom sklearn.neighbors import KNeighborsRegressornfrom sklearn.ensemble import RandomForestRegressornfrom sklearn.ensemble import GradientBoostingRegressor, AdaBoostRegressornfrom xgboost import XGBRegressornfrom sklearn.preprocessing import PolynomialFeatures, MinMaxScaler, StandardScaler

2.数据载入

pd.set_option("display.max_rows", None) # None时不限制数量npd.set_option("display.max_columns", None)npd.set_option("display.width", 1000)nplt.rcParams["axes.unicode_minus"] = Falsensns.set_style("white", {"font.sans-serif": ["simhei", "Arial"]}) # 解决中文不能显示问题nnndata_train = pd.read_csv("./zhengqi_train.txt", sep="t", encoding="utf-8")ndata_test = pd.read_csv("./zhengqi_test.txt", sep="t", encoding="utf-8")ndata_train["oringin"] = "train"ndata_test["oringin"] = "test"ndata_all = pd.concat([data_train, data_test], axis=0, ignore_index=True)n# print(data_all.head())n# print(data_all.tail())

3.数据探查

3.1训练集和测试集数据分布

for col in data_all.columns[0:-2]:n g = sns.kdeplot(data_all[col][(data_all["oringin"] == "train")], color="Red", shade=True)n g = sns.kdeplot(data_all[col][(data_all["oringin"] == "test")], color="Blue", shade=True, ax=g)n g.set_xlabel(col)n g.set_ylabel("Frequency")n g.legend(["train", "test"])n plt.show()

删除特征V5,V9,V11,V17,V22,V28

data_all.drop(["V5", "V9", "V11", "V17", "V22", "V28"], axis=1, inplace=True)

再看下数据分布情况：

data_train1 = data_all[data_all["oringin"] == "train"].drop("oringin", axis=1)nfcols = 2nfrows = len(data_train1.columns)nplt.figure(figsize=(5 * fcols, 4 * frows))ni = 0nfor col in data_train1.columns:n i += 1n ax = plt.subplot(frows, fcols, i)n sns.regplot(n x=col,n y="target",n data=data_train,n ax=ax,n scatter_kws={"marker": ".", "s": 3, "alpha": 0.3},n line_kws={"color": "k"},n )n plt.xlabel(col)n plt.ylabel("target")n i += 1n ax = plt.subplot(frows, fcols, i)n sns.distplot(data_train[col].dropna(), fit=stats.norm)n plt.xlabel(col)nplt.show()

# 找出相关程度nplt.figure(figsize=(20, 16)) # 指定绘图对象宽度和高度ncolnm = data_train1.columns.tolist() # 列表头nmcorr = data_train1[colnm].corr(method="spearman") # 相关系数矩阵，即给出了任意两个变量之间的相关系数nmask = np.zeros_like(mcorr, dtype=np.bool) # 构造与mcorr同维数矩阵 为bool型nmask[np.triu_indices_from(mask)] = True # 角分线右侧为Truencmap = sns.diverging_palette(220, 10, as_cmap=True) # 返回matplotlib colormap对象ng = sns.heatmap(n mcorr, mask=mask, cmap=cmap, square=True, annot=True, fmt="0.2f"n) # 热力图（看两两相似度）nplt.show()

将与target的相关性绝对值<0.1的列剔除：

# Threshold for removing correlated variablesnthreshold = 0.1n# Absolute value correlation matrixncorr_matrix = data_train1.corr().abs()ndrop_col = corr_matrix[corr_matrix["target"] < threshold].indexnprint(drop_col)ndata_all.drop(drop_col, axis=1, inplace=True)nprint(data_all.columns)

标准正态化：

# normalise numeric columnsncols_numeric = list(data_all.columns)ncols_numeric.remove("oringin")nnn# 计算标准分数ndef scale_minmax(col):n return (col - col.min()) / (col.max() - col.min())nnnscale_cols = [col for col in cols_numeric if col != "target"]ndata_all[scale_cols] = data_all[scale_cols].apply(scale_minmax, axis=0)nprint(data_all[scale_cols].describe())

Box-Cox变换：

# Check effect of Box-Cox transforms on distributions of continuous variablesnfcols = 6nfrows = len(cols_numeric) - 1nplt.figure(figsize=(4 * fcols, 4 * frows))ni = 0nfor var in cols_numeric:n if var != "target":n dat = data_all[[var, "target"]].dropna()n i += 1n plt.subplot(frows, fcols, i)n sns.distplot(dat[var], fit=stats.norm)n plt.title(var + " Original")n plt.xlabel("")nn i += 1n plt.subplot(frows, fcols, i)n _ = stats.probplot(dat[var], plot=plt)n plt.title("skew=" + "{:.4f}".format(stats.skew(dat[var])))n plt.xlabel("")n plt.ylabel("")nn i += 1n plt.subplot(frows, fcols, i)n plt.plot(dat[var], dat["target"], ".", alpha=0.5)n plt.title("corr=" + "{:.2f}".format(np.corrcoef(dat[var], dat["target"])[0][1]))nn i += 1n plt.subplot(frows, fcols, i)n trans_var, lambda_var = stats.boxcox(dat[var].dropna() + 1)n trans_var = scale_minmax(trans_var)n sns.distplot(trans_var, fit=stats.norm)n plt.title(var + " Tramsformed")n plt.xlabel("")nn i += 1n plt.subplot(frows, fcols, i)n _ = stats.probplot(trans_var, plot=plt)n plt.title("skew=" + "{:.4f}".format(stats.skew(trans_var)))n plt.xlabel("")n plt.ylabel("")nn i += 1n plt.subplot(frows, fcols, i)n plt.plot(trans_var, dat["target"], ".", alpha=0.5)n plt.title(n "corr=" + "{:.2f}".format(np.corrcoef(trans_var, dat["target"])[0][1])n )nplt.show()

变换：

for col in cols_transform:n data_all.loc[:, col], _ = stats.boxcox(data_all.loc[:, col] + 1)n"""print(data_all.target.describe())nplt.figure(figsize=(12, 4))nplt.subplot(1, 2, 1)nsns.distplot(data_all.target.dropna(), fit=stats.norm)nplt.subplot(1, 2, 2)n_ = stats.probplot(data_all.target.dropna(), plot=plt)nplt.show()"""

转换：

# Log Transform SalePrice to improve normalitynsp = data_train.targetndata_train.target1 = np.power(1.5, sp)nprint(data_train.target1.describe())

for column in data_all.columns[0:-2]:n g = sns.kdeplot(n data_all[column][(data_all["oringin"] == "train")], color="Red", shade=Truen )n g = sns.kdeplot(n data_all[column][(data_all["oringin"] == "test")],n ax=g,n color="Blue",n shade=True,n )n g.set_xlabel(column)n g.set_ylabel("Frequency")n g = g.legend(["train", "test"])n plt.show()