In [2]:
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
sns.set()
In [8]:
df = pd.read_csv("../data/cleaned_coalpublic2013.xls", index_col='MSHA ID')
df.head()
len(df)
Out[8]:
In [10]:
for column in df.columns:
print column
In [11]:
df.log_production.hist()
Out[11]:
In [12]:
df.Mine_Status.unique()
Out[12]:
In [15]:
df[['Mine_Status', 'log_production']].groupby('Mine_Status').mean()
Out[15]:
In [26]:
features = ['Average_Employees',
'Labor_Hours'
]
categoricals = ['Mine_State',
'Mine_County',
'Mine_Status',
'Mine_Type',
'Company_Type',
'Operation_Type',
'Union_Code',
'Coal_Supply_Region',
]
target = 'log_production'
In [18]:
fig = plt.subplots(figsize=(14,8))
sns.set_context('poster')
sns.violinplot(y='Mine_Status', x='log_production', data=df,
split=True, inner='stick', )
plt.tight_layout()
In [19]:
fig = plt.subplots(figsize=(14,8))
sns.set_context('poster')
sns.violinplot(y='Company_Type', x='log_production', data=df,
split=True, inner='stick', )
plt.tight_layout()
In [20]:
df['Company_Type'].unique()
Out[20]:
In [22]:
pd.get_dummies(df['Company_Type']).sample(50).head()
Out[22]:
In [27]:
dummy_categoricals =[]
for categorical in categoricals:
print categorical, len(df[categorical].unique())
# Avoid the dummy variable trap!
drop_var = sorted(df[categorical].unique())[-1]
temp_df = pd.get_dummies(df[categorical], prefix=categorical)
df = pd.concat([df, temp_df], axis=1)
temp_df.drop('_'.join([categorical, str(drop_var)]), axis=1, inplace=True)
dummy_categoricals += temp_df.columns.tolist()
In [28]:
dummy_categoricals[:10]
Out[28]:
In [29]:
from sklearn.cross_validation import train_test_split
from sklearn.ensemble import RandomForestRegressor
In [30]:
len(dummy_categoricals)
Out[30]:
In [31]:
train, test = train_test_split(df, test_size=0.3)
In [33]:
rf = RandomForestRegressor(n_estimators=100, oob_score=True)
In [34]:
rf.fit(train[features + dummy_categoricals], train[target])
Out[34]:
In [37]:
fit = plt.subplots(figsize=(8,8))
sns.regplot(test[target], rf.predict(test[features + dummy_categoricals]))
plt.xlim(0,22)
plt.xlabel("Actual Production")
plt.ylabel("Predicted Production")
plt.ylim(0,22)
plt.tight_layout()
In [38]:
from sklearn.metrics import explained_variance_score, r2_score, mean_squared_error
In [40]:
predicted = rf.predict(test[features + dummy_categoricals])
r2_score(test[target], predicted)
Out[40]:
In [41]:
explained_variance_score(test[target], predicted)
Out[41]:
In [42]:
mean_squared_error(test[target], predicted)
Out[42]:
In [44]:
rf_importances = pd.DataFrame({'name':train[features + dummy_categoricals].columns,
'importance':rf.feature_importances_}).sort_values(by='importance',
ascending=False).reset_index(drop=True)
rf_importances.head(20)
Out[44]:
In [ ]: