用Plotily处理数据的基本操作

import pandas as pd
# 导入数据.scv
df = pd.read_csv(" .csv")
# 查看前五行数据
df.head()
# 查看一下数据描述
df.descirbe()
# 查看一下数据的形状
df.shape
# 查看一下数据集中都包含哪些列
df.columns 

# 对数据进行可视化
import matplotlib.pyplot as plt
import seaborn as sns
# 使用Jupyter Notebook
# import warnings
# warnings.filterwarnings("ignore")
# %matplotlib inline

# 创建自定义图像
figure(num=None, figsize=None, dpi=None, facecolor=None, edgecolor=None, frameon=True)
# 标题
plt.title(" ")
# 画出数据分布图
sns.displot(df[" "]) 

# !pip install plotly # 安装Plotily库
# 导入绘图工具库
import plotly.offline as offline
import plotly.graph_objs as go
import plotly.offline as py
from plotly.offline import init_notebook_mode, iplot
init_notebook_mode(connected=True)
offline.init_notebook_mode()

# 查看表格某列中有多少个不同值的快捷方法，并计算每个不同值有在该列中有多少重复值
temp = df[" "].value_counts()
# 画出柱状图，查看不同值所占比重
trace = [go.Bar(x = temp.index, y = (temp / temp.sum()) * 100)]
# 设置图的字体颜色等
layout = go.Layout(
    title=" ",
    xaxis=dict(title=' ',
               tickfont=dict(size= , color='rgb(  ,  ,  )')),
    yaxis=dict(title=' ',
               titlefont=dict(size= , color='rgb(  ,  ,  )'),
               tickfont=dict(size= , color='rgb(  ,  ,  )'))
)
# 显示图形
fig = go.Figure(data=trace, layout=layout)
iplot(fig, filename=' ')

# 画出饼状图
trace = [go.Pie(labels=temp.index, values=temp.values)]
# 设置图题
layout = go.Layout(
    title=' ',
)
# 显示图形
fig = go.Figure(data=trace, layout=layout)
iplot(fig)

# 画出饼状图，圆环型
trace = [go.Pie(labels=temp.index, values=temp.values, hole=0.6)]

temp1 = df["FLAG_OWN_CAR"].value_counts()
temp2 = df["FLAG_OWN_REALTY"].value_counts()

# 画出两个饼状图
trace = [go.Pie(labels=temp1.index, values=temp1.values, domain={"x": [0, .48]}, hole=0.6),
         go.Pie(labels=temp2.index, values=temp2.values, domain={"x": [0.5, 1]}, hole=0.6)]
# 设置图中的字体，图题等
layout = go.Layout(
    title=' ',
    annotations=[{"font": {
        "size":  },
        "showarrow":  ,
        "text": " ",
        "x": 0. , # 坐标
        "y": 0. },
        {"font": {
         "size": },
         "showarrow": ,
         "text": " ",
         "x": 0. ,
         "y": 0. }])
# 显示图形
fig = go.Figure(data=trace, layout=layout)
iplot(fig)

# 计数方法
temp_y0 = []
temp_y1 = []
for val in temp.index:
    temp_y1.append(np.sum(df["TARGET"][df["TYPE"] == val] == 1))
    temp_y0.append(np.sum(df["TARGET"][df["TYPE"] == val] == 0))
temp_y1 = np.array(temp_y1)
temp_y0 = np.array(temp_y0)

# 删除掉存在缺失值的特征列
df_drop = df.dropna(axis=1)
df_drop.head()

# 将其编码成为数值形式
from sklearn import preprocessing
# 取出非数值的列
categorical_feats = [
    f for f in df_drop.columns if df_drop[f].dtype == 'object'
]
# 对非数值的列进行编码
for col in categorical_feats:
    lb = preprocessing.LabelEncoder()
    lb.fit(list(df_drop[col].values.astype('str')))
    df_drop[col] = lb.transform(list(df_drop[col].values.astype('str')))
df_drop.head()

# 划分数据
# 删除ID
df_drop1 = df_drop.drop("ID", axis=1)
# 提取训练特征数据和目标值
data_X = df_drop1.drop(" ", axis=1)
data_y = df_drop1[' ']
#划分数据集为训练数据集和测试数据集
from sklearn import model_selection
train_x, test_x, train_y, test_y = model_selection.train_test_split(data_X.values, data_y.values, test_size=0.8, random_state=0)

# 构建预测模型
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier()  # 构建模型
model.fit(train_x, train_y)  # 训练模型
from sklearn import metrics
y_pred = model.predict(test_x)  # 预测测试集
metrics.accuracy_score(y_pred, test_y)  # 评价预测结果
print(metrics.classification_report(y_pred, test_y))

features = data_X.columns.values  # 取出数据集中的列名，即特征名
# 得到特征与其重要性
x, y = (list(x) for x in zip(*sorted(zip(model.feature_importances_, features), reverse=False)))
# 画出柱状图
trace2 = go.Bar(x=x, y=y, marker=dict(color=x, colorscale='Viridis', reversescale=True), name=' ', orientation='h',)
# 设置图题、字体等
layout = dict(title=' ', width=900, height=2000,
              yaxis=dict(showgrid=False, showline=False, showticklabels=True,), margin=dict(l=300,))
# 显示图形
fig1 = go.Figure(data=[trace2])
fig1['layout'].update(layout)
iplot(fig1, filename='plots')

from sklearn.tree import DecisionTreeClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.linear_model import LogisticRegression

# 构建 7 种算法
models = [LogisticRegression(solver='lbfgs'),       # 逻辑回归
          RandomForestClassifier(n_estimators=100),  # 随机森林
          DecisionTreeClassifier(),                 # 决策树
          MLPClassifier(max_iter=100),              # 多层感知机
          AdaBoostClassifier(),                     # 自适应梯度提升
          BaggingClassifier(),                      # 装袋算法
          GradientBoostingClassifier()]             # 梯度提升算法

model_name = ['LogisticRegression',
              'RandomForestClassifier',
              "DecisionTreeClassifier",
              'MLPClassifier',
              'AdaBoostClassifier',
              'BaggingClassifier',
              'GradientBoostingClassifier']

acc = []        # 存放各算法的准确率
f1 = []         # 存放各算法的 f1 值
recall = []     # 存放各算法的召回率

for model in models:  # 训练每个算法
    model.fit(train_x, train_y)
    acc.append(model.score(test_x, test_y))
    y_pred = model.predict(test_x)
    f1.append(metrics.f1_score(y_pred, test_y))
    recall.append(metrics.recall_score(y_pred, test_y))

# 打印每种算法的评估结果
pd.DataFrame({"name": model_name, "acc": acc, "f1": f1, "recall": recall})