#load csv into dataframe
%matplotlib inline
import pandas as pd

boston_df = pd.read_csv("/Users/rcphillips/Documents/Data/Boston.csv")

#inspect data for quality
boston_df.head()

#import modelling package
from sklearn import linear_model

#predict medv using lstat
import numpy as np
lm = linear_model.LinearRegression()
#predictor value:
X=np.transpose(np.matrix(boston_df.lstat.values))
#value being estimated:
y=np.transpose(np.matrix(boston_df.medv.values))

lm.fit(X,y)

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

#gotta reshape the data  to fit it into the sklearn inputs
np.shape(boston_df.medv.values)

(506,)

np.shape(np.matrix(boston_df.medv.values))

(1, 506)

np.shape(np.transpose(np.matrix(boston_df.medv.values)))

(506, 1)

predictions=lm.predict(np.transpose(np.matrix(boston_df.lstat.values)))

side_by_side = pd.DataFrame(boston_df.medv)

side_by_side['predictions']=predictions

side_by_side['residuals']=side_by_side.medv-side_by_side.predictions

side_by_side

#extract interesting model features.
coef=lm.coef_
print('Coefficients: \n', coef)
from scipy import stats
slope, intercept, r_value, p_value, std_err = stats.linregress(list(boston_df.lstat.values), list(boston_df.medv.values))

print('slope,            intercept,      r_value,       p_value,        std_err' )
print(slope, intercept, r_value, p_value, std_err )

Coefficients: 
 [[-0.95004935]]
slope,            intercept,      r_value,       p_value,        std_err
-0.950049353758 34.5538408794 -0.737662726174 5.08110339439e-88 0.0387334162126

#plot data, and line of best fit
import matplotlib.pyplot as plt
lstat = list(boston_df.lstat.values)
medv= list(boston_df.medv.values)
a=plt.scatter(lstat,medv)
plt.plot(lstat,predictions, color='red')

[<matplotlib.lines.Line2D at 0x1108115c0>]

#plotting residuals
import seaborn as sns

sns.regplot(side_by_side.medv, side_by_side.predictions)

<matplotlib.axes._subplots.AxesSubplot at 0x1142f0128>

sns.regplot(side_by_side.medv, side_by_side.residuals)

<matplotlib.axes._subplots.AxesSubplot at 0x114309400>

#predict medv using lstat and crim
import numpy as np
lm = linear_model.LinearRegression()
#predictor value:
X=np.transpose(np.matrix(boston_df.lstat.values))
#value being estimated:
a=np.transpose(np.matrix(boston_df.medv.values))
b=np.transpose(np.matrix(boston_df.crim.values))
y=np.append(a,b,1)

lm.fit(X,y)

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

coef=lm.coef_

import statsmodels.formula.api as smf

smf.OLS(X,y)

<statsmodels.regression.linear_model.OLS at 0x114977080>

results=smf.OLS('crim ~ crim ', boston_df).fit()

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-24-6996c1147a45> in <module>()
----> 1 results=smf.OLS('crim ~ crim ', boston_df).fit()


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
    629                  **kwargs):
    630         super(OLS, self).__init__(endog, exog, missing=missing,
--> 631                                   hasconst=hasconst, **kwargs)
    632         if "weights" in self._init_keys:
    633             self._init_keys.remove("weights")


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, weights, missing, hasconst, **kwargs)
    524             weights = weights.squeeze()
    525         super(WLS, self).__init__(endog, exog, missing=missing,
--> 526                                   weights=weights, hasconst=hasconst, **kwargs)
    527         nobs = self.exog.shape[0]
    528         weights = self.weights


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/regression/linear_model.py in __init__(self, endog, exog, **kwargs)
     93     """
     94     def __init__(self, endog, exog, **kwargs):
---> 95         super(RegressionModel, self).__init__(endog, exog, **kwargs)
     96         self._data_attr.extend(['pinv_wexog', 'wendog', 'wexog', 'weights'])
     97


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
    210 
    211     def __init__(self, endog, exog=None, **kwargs):
--> 212         super(LikelihoodModel, self).__init__(endog, exog, **kwargs)
    213         self.initialize()
    214


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/model.py in __init__(self, endog, exog, **kwargs)
     61         hasconst = kwargs.pop('hasconst', None)
     62         self.data = self._handle_data(endog, exog, missing, hasconst,
---> 63                                       **kwargs)
     64         self.k_constant = self.data.k_constant
     65         self.exog = self.data.exog


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/model.py in _handle_data(self, endog, exog, missing, hasconst, **kwargs)
     86 
     87     def _handle_data(self, endog, exog, missing, hasconst, **kwargs):
---> 88         data = handle_data(endog, exog, missing, hasconst, **kwargs)
     89         # kwargs arrays could have changed, easier to just attach here
     90         for key in kwargs:


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/data.py in handle_data(endog, exog, missing, hasconst, **kwargs)
    628     klass = handle_data_class_factory(endog, exog)
    629     return klass(endog, exog=exog, missing=missing, hasconst=hasconst,
--> 630                  **kwargs)


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/data.py in __init__(self, endog, exog, missing, hasconst, **kwargs)
     74             self.orig_endog = endog
     75             self.orig_exog = exog
---> 76             self.endog, self.exog = self._convert_endog_exog(endog, exog)
     77 
     78         # this has side-effects, attaches k_constant and const_idx


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/data.py in _convert_endog_exog(self, endog, exog)
    471             raise ValueError("Pandas data cast to numpy dtype of object. "
    472                              "Check input data with np.asarray(data).")
--> 473         return super(PandasData, self)._convert_endog_exog(endog, exog)
    474 
    475     @classmethod


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/data.py in _convert_endog_exog(self, endog, exog)
    310 
    311         # for consistent outputs if endog is (n,1)
--> 312         yarr = self._get_yarr(endog)
    313         xarr = None
    314         if exog is not None:


/Users/rcphillips/anaconda3/lib/python3.5/site-packages/statsmodels/base/data.py in _get_yarr(self, endog)
    385             endog = data_util.struct_to_ndarray(endog)
    386         endog = np.asarray(endog)
--> 387         if len(endog) == 1:  # never squeeze to a scalar
    388             if endog.ndim == 1:
    389                 return endog


TypeError: len() of unsized object

boston_df.columns

Index(['crim', 'zn', 'indus', 'chas', 'nox', 'rm', 'age', 'dis', 'rad', 'tax',
       'ptratio', 'black', 'lstat', 'medv'],
      dtype='object')