feature importance

# coding: utf-8

# In[1]:


import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
from sklearn.ensemble import RandomForestRegressor
from sklearn.linear_model import LinearRegression


# In[2]:


x1 = np.linspace(0,1, num=50);
x2 = np.linspace(0,1, num=50);


# In[3]:


x1


# In[4]:


x1.shape


# In[5]:


np.random.seed(42)
y = 2*x1 + 0.1*x2  + np.random.uniform(-0.1, 0.1, x1.shape)


# In[6]:


df = pd.DataFrame()
df['x1']=x1; df['x2']=x2; df['y']=y;
df.head()


# In[7]:


m = RandomForestRegressor(n_estimators=10)


# In[8]:


X,y = df.drop('y', axis=1), df['y']


# In[9]:


X.head()


# In[10]:


y.head()


# In[11]:


X_train, X_val = X[:40], X[40:]
y_train, y_val = y[:40], y[40:]


# In[12]:


m.fit(X_train, y_train)


# In[13]:


m.feature_importances_


# In[14]:


fi = pd.DataFrame(m.feature_importances_, index = X_train.columns, columns=['importance']); fi