def score(df):
X, y = get_X_y(df)
vif = variance_inflation_factor
print('VIF: ')
for i in range(X.shape[1]):
print(vif(X, i))
X = add_constant(X)
model = Logit(y, X).fit()
print(model.summary(xname=names))
kfold = KFold(n_splits=5)
accuracies = []
precisions = []
recalls = []
for train_index, test_index in kfold.split(X):
model = LogisticRegression(solver="lbfgs")
model.fit(X[train_index], y[train_index])
y_predict = model.predict(X[test_index])
y_true = y[test_index]
accuracies.append(accuracy_score(y_true, y_predict))
precisions.append(precision_score(y_true, y_predict))
recalls.append(recall_score(y_true, y_predict))
print("Accuracy:", np.average(accuracies))
print("Precision:", np.average(precisions))
print("Recall:", np.average(recalls))
def basic_significance(dataframe, list_to_dummify, target):
'''
fits a non-regularized logistic model to target using dataframe predictors
prints model accuracy and outputs significant coefficients order by absolute magnitude
----------
list_to_dummify: a list of columns in string format that require dummification before modeling
'''
#process the dataframe
df = dataframe.copy()
df = dummify_columns(df, list_to_dummify)
X, y = xy_split(df, target)
X = add_constant(X)
#fit the model
logit = Logit(y, X)
fitted_logit = Logit.fit(logit)
#store accuracy
c_mat = confusion_matrix(
y, np.round(Logit.predict(logit, fitted_logit.params)))
accuracy = sum(c_mat.diagonal()) / np.sum(c_mat)
print('model train accuracy: %s' % (accuracy))
#store significant coefs
coefs = pd.DataFrame(fitted_logit.pvalues[fitted_logit.pvalues < 0.05])
coefs['coefs'] = fitted_logit.params.filter(items=coefs.index)
coefs.columns = ['p-values', 'coefs']
coefs['abs_coefs'] = np.abs(coefs.coefs)
coefs = coefs.sort_values(by='abs_coefs', ascending=False)
coefs = coefs.drop('abs_coefs', axis=1)
return fitted_logit, coefs
def SM_logit(X, y):
"""Computing logit function using statsmodels Logit and
output is coefficient array."""
logit = Logit(y, X)
result = logit.fit()
coeff = result.params
return coeff
def runAnalysis(self,y): log_res=[0 for i in range(0,self.m)]; for i in range(0,self.m): I=[i] I.extend([-1]) x=self.X[:,I]; lr=LR(y,x); res_lr=lr.fit(disp=0) if self.params=="Coef": log_res[i]=float(res_lr.params[0]); if self.params=="Odds": coef=float(res_lr.params[0]); log_res[i]=math.exp(coef); """ if self.params=="pval": log_res[i]=; if self.params=="logpval": pval=; if pval>0: log_res[i]=-np.log10(pval); else: log_res[i]=-1.0; """ return np.asarray(log_res);
def test_attack(n0, n1, numCov, err=.001):
n = n0 + n1
x = [rand.randint(0, 2) for i in range(0, n)]
y = [1 for i in range(0, n)]
for i in range(0, n0):
y[i] = 0
covs = [[rand.randint(0, 1) for i in range(0, n)]
for j in range(0, numCov)]
ORs = []
for i in range(0, numCov):
print i
ret = [x]
ret.append(covs[i])
X = np.asarray(ret).T
X = AC(X, False)
lr = LR(y, X)
res_lr = lr.fit(disp=0)
OR = math.exp(float(res_lr.params[0]))
ret.append(attack(y, covs, OR, err))
ORs.append(OR)
print "The number of matches is: "
for r in ret:
str(len(r))
print ORs
for r in ret:
print r
print len(ret)
def forward_selection(dataframe, target, list_to_dummify, criteria='bic'):
'''
runs forward selection process to select best predictor set based on bic or aic
returns a dictionary with the variable set and aic/bic at each step
----------
criteria: default value bic, otherwise aic is used
list_to_dummify: a list of columns in string format that require dummification before modeling
'''
#create target array, intercept only dataframe, and list of variables to select from
X = pd.DataFrame()
y = dataframe[target]
X['const'] = np.ones(cchd.shape[0])
var_list = list(dataframe.columns)
var_list.remove(target)
#create empty dictionary to store output of each step
models = {'model_vars': [], 'scoring_crit': []}
#define while loop that will run until all variables have been selected
while len(var_list) > 0:
#define empty list to store aic/bic values temporarily for step attempt
crit_vals = []
#try adding variables one by one find lowest vif model for current step
for var in var_list:
#create temporary df with all previously selected variables + the new variable being tried
tempX = pd.concat([X, dataframe[var]], axis=1)
#dummify the variable if necessary
if var in list_to_dummify:
tempX = dummify_columns(tempX, [var])
#fit the logistic model
logit = Logit(y, tempX)
fitted_logit = Logit.fit(logit)
#store aic or bic in a list for each variable attempted
if criteria == 'bic':
crit_vals += [fitted_logit.bic]
else:
crit_vals += [fitted_logit.aic]
#find the index of the lowest bic model and store the name of the variable which produced it
min_crit_idx = crit_vals.index(min(crit_vals))
best_var = var_list[min_crit_idx]
#add the best variable to the df
X = pd.concat([X, dataframe[best_var]], axis=1)
#store the variables and aic/bic for the best model at the current step
models['model_vars'] += [list(X.columns)]
models['scoring_crit'] += [min(crit_vals)]
#dummify the added variable if necessary
if best_var in list_to_dummify:
X = dummify_columns(X, [best_var])
#remove the added variable from the variable list and track progress
var_list.remove(best_var)
print('adding var: %s' % (best_var))
return models
def score(self, X, confounder_types, assignment='assignment', store_model_fit=False, intercept=True):
df = X[[assignment]]
regression_confounders = []
for confounder, var_type in confounder_types.items():
if var_type == 'o' or var_type == 'u':
c_dummies = pd.get_dummies(X[[confounder]], prefix=confounder)
if len(c_dummies.columns) == 1:
df[c_dummies.columns] = c_dummies[c_dummies.columns]
regression_confounders.extend(c_dummies.columns)
else:
df[c_dummies.columns[1:]] = c_dummies[c_dummies.columns[1:]]
regression_confounders.extend(c_dummies.columns[1:])
else:
regression_confounders.append(confounder)
df.loc[:,confounder] = X[confounder].copy() #
df.loc[:,confounder] = X[confounder].copy() #
if intercept:
df.loc[:,'intercept'] = 1.
regression_confounders.append('intercept')
logit = Logit(df[assignment], df[regression_confounders])
result = logit.fit()
if store_model_fit:
self.model_fit = result
X.loc[:,'propensity score'] = result.predict(df[regression_confounders])
return X
def test_perfect_prediction():
cur_dir = os.path.dirname(os.path.abspath(__file__))
iris_dir = os.path.join(cur_dir, '..', '..', 'genmod', 'tests', 'results')
iris_dir = os.path.abspath(iris_dir)
iris = np.genfromtxt(os.path.join(iris_dir, 'iris.csv'), delimiter=",",
skip_header=1)
y = iris[:,-1]
X = iris[:,:-1]
X = X[y != 2]
y = y[y != 2]
X = sm.add_constant(X, prepend=True)
mod = Logit(y,X)
assert_raises(PerfectSeparationError, mod.fit)
#turn off raise PerfectSeparationError
mod.raise_on_perfect_prediction = False
mod.fit(disp=False) #should not raise
def test_perfect_prediction():
cur_dir = os.path.dirname(os.path.abspath(__file__))
iris_dir = os.path.join(cur_dir, '..', '..', 'genmod', 'tests', 'results')
iris_dir = os.path.abspath(iris_dir)
iris = np.genfromtxt(os.path.join(iris_dir, 'iris.csv'), delimiter=",",
skip_header=1)
y = iris[:,-1]
X = iris[:,:-1]
X = X[y != 2]
y = y[y != 2]
X = sm.add_constant(X, prepend=True)
mod = Logit(y,X)
assert_raises(PerfectSeparationError, mod.fit)
#turn off raise PerfectSeparationError
mod.raise_on_perfect_prediction = False
mod.fit(disp=False) #should not raise
def logreg(X, y, train_test=True, roc=True):
'''
INPUT:
- X: 2-D feature matrix
- y: target vector
- train_test: boolean
- roc: boolean
OUTPUT:
- fitted: fitted LogitResults
Runs statsmodels Logistic Regression and prints summary. Uses
train_test_split to split data if train_test = True. Plots and shows ROC
curve if roc = True. Returns fitted Logistic Regression model.
'''
if train_test:
X_train, X_test, y_train, y_test = train_test_split(X, y)
else:
X_train, X_test, y_train, y_test = X, X, y, y
vifs, filtered = get_vifs(X_train)
X_train, X_test = X_train[filtered], X_test[filtered]
log_reg = Logit(y_train, add_constant(X_train, has_constant='add'))
fitted = log_reg.fit(method='bfgs', maxiter=500)
try:
print fitted.summary()
except:
return logreg(X, y)
if roc:
plot_roc(y_test, fitted.predict(add_constant(X_test, has_constant='add')))
return fitted
def score(self,
X,
confounder_types,
assignment='assignment',
store_model_fit=False,
intercept=True):
df = X[[assignment]]
regression_confounders = []
for confounder, var_type in confounder_types.items():
if var_type == 'o' or var_type == 'u':
c_dummies = pd.get_dummies(X[[confounder]], prefix=confounder)
if len(c_dummies.columns) == 1:
df[c_dummies.columns] = c_dummies[c_dummies.columns]
regression_confounders.extend(c_dummies.columns)
else:
df[c_dummies.columns[1:]] = c_dummies[
c_dummies.columns[1:]]
regression_confounders.extend(c_dummies.columns[1:])
else:
regression_confounders.append(confounder)
df.loc[:, confounder] = X[confounder].copy() #
df.loc[:, confounder] = X[confounder].copy() #
if intercept:
df.loc[:, 'intercept'] = 1.
regression_confounders.append('intercept')
logit = Logit(df[assignment], df[regression_confounders])
result = logit.fit()
if store_model_fit:
self.model_fit = result
X.loc[:,
'propensity score'] = result.predict(df[regression_confounders])
return X
def test_attributes(self):
data = ds.df
mask_drop = data['apply'] == "somewhat likely"
data2 = data.loc[~mask_drop, :].copy()
# we need to remove the category also from the Categorical Index
data2['apply'] = data2['apply'].cat.remove_categories(
"somewhat likely")
# standard fit with pandas input
modp = OrderedModel(data2['apply'],
data2[['pared', 'public', 'gpa']],
distr='logit')
resp = modp.fit(method='bfgs', disp=False)
exog = add_constant(data2[['pared', 'public', 'gpa']], prepend=False)
mod_logit = Logit(data2['apply'].cat.codes, exog)
res_logit = mod_logit.fit()
attributes = "bse df_resid llf aic bic llnull".split()
attributes += "llnull llr llr_pvalue prsquared".split()
assert_allclose(resp.params[:3], res_logit.params[:3], rtol=1e-5)
assert_allclose(resp.params[3], -res_logit.params[3], rtol=1e-5)
for attr in attributes:
assert_allclose(getattr(resp, attr),
getattr(res_logit, attr),
rtol=1e-4)
resp = modp.fit(method='bfgs',
disp=False,
cov_type="hac",
cov_kwds={"maxlags": 2})
res_logit = mod_logit.fit(method='bfgs',
disp=False,
cov_type="hac",
cov_kwds={"maxlags": 2})
for attr in attributes:
assert_allclose(getattr(resp, attr),
getattr(res_logit, attr),
rtol=1e-4)
resp = modp.fit(method='bfgs', disp=False, cov_type="hc1")
res_logit = mod_logit.fit(method='bfgs', disp=False, cov_type="hc1")
for attr in attributes:
assert_allclose(getattr(resp, attr),
getattr(res_logit, attr),
rtol=1e-4)
def Log_Calc(y, x):
x1 = AC(x, False)
lr = LR(y, x1)
try:
res_lr = lr.fit(disp=0)
except:
return -1
return math.exp(res_lr.params[0])
def log_reg(X_train, Y_train, X_val):
from statsmodels.discrete.discrete_model import Logit
from statsmodels.tools import add_constant
X_train = add_constant(X_train)
X_val = add_constant(X_val)
logit = Logit(Y_train, X_train)
fit = logit.fit(method = 'bfgs', maxiter = 10000)
logitprobs = fit.predict(X_val)
return logitprobs
def select_features(X, y):
if len(list(set(list(y)))) == 2:
model = Logit(y, X)
else:
model = OLS(y, X)
res = model.fit(disp = False)
features = ind = multitest.multipletests(res.pvalues, method='holm')[0]
X = X[:, features]
return X
def get_logit_coef(X, y, cols=None):
if cols:
X_fit = X[cols]
else:
X_fit = X
X_fit = sm.add_constant(X_fit)
logit = Logit(y, X_fit)
fit = logit.fit()
print fit.summary()
class LogisticRegression(object):
def __init__(self):
pass
def fit(self, X, y, **kwargs):
self.model = Logit(y, X)
self.result = self.model.fit()
def predict_proba(self, X):
return self.result.predict(X)
def _initialize(cls):
y, x = cls.y, cls.x
modp = Logit(y, x)
cls.res2 = modp.fit(disp=0)
mod = LogitPenalized(y, x, penal=cls.penalty)
mod.pen_weight = 0
cls.res1 = mod.fit(disp=0)
cls.atol = 1e-4 # why not closer ?
class LogisticRegression(object):
def __init__(self):
pass
def fit(self, X, y, **kwargs):
from statsmodels.discrete.discrete_model import Logit
self.model = Logit(y, X)
self.result = self.model.fit()
def predict_proba(self, X):
return self.result.predict(X)
def _initialize(cls):
y, x = cls.y, cls.x
modp = Logit(y, x)
cls.res2 = modp.fit(disp=0)
mod = LogitPenalized(y, x, penal=cls.penalty)
mod.pen_weight = 0
cls.res1 = mod.fit(disp=0)
cls.atol = 1e-4 # why not closer ?
class LogisticRegression(object):
def __init__(self):
pass
def fit(self, X, y, **kwargs):
from statsmodels.discrete.discrete_model import Logit
self.model = Logit(y, X)
self.result = self.model.fit()
def predict_proba(self, X):
return self.result.predict(X)
def logregress(xi, xj, *args, **kwargs):
x = np.vstack((xi, xj))[::3]
y = np.vstack((np.zeros((xi.shape[0], 1)), np.ones((xj.shape[0], 1))))[::3]
scaler = MinMaxScaler([-1, 1])
scaler.fit(x)
x = scaler.transform(x)
#clf = LogisticRegression(random_state=0).fit(x, y[:, 0])
model = Logit(y, x)
res = model.fit()
#print(res.prsquared)
return res.prsquared
def setup_class(cls):
df = data_bin
mod = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial())
res = mod.fit(method="newton", tol=1e-10)
from statsmodels.discrete.discrete_model import Logit
mod2 = Logit(df['constrict'], df[['const', 'log_rate', 'log_volumne']])
res2 = mod2.fit(method="newton", tol=1e-10)
cls.infl1 = res.get_influence()
cls.infl0 = res2.get_influence()
def create_Logit(X, y):
'''
creates statsmodels logistic regression model with 'linked click ' as target variable
INPUT: pandas dataframe
OUTPUT: statsmodels Logistic Regression model
'''
X = X.copy()
X['constant'] = 1
X.pop('email_id')
logit = Logit(y, X)
model = logit.fit(maxiter=400)
return model
def _initialize(cls):
y, x = cls.y, cls.x
modp = Logit(y, x[:, :cls.k_nonzero])
cls.res2 = modp.fit(disp=0)
mod = LogitPenalized(y, x, penal=cls.penalty)
mod.pen_weight *= .5
mod.penal.tau = 0.05
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.exog_index = slice(None, cls.k_nonzero, None)
cls.atol = 5e-3
def _initialize(cls):
y, x = cls.y, cls.x
modp = Logit(y, x[:, :cls.k_nonzero])
cls.res2 = modp.fit(disp=0)
mod = LogitPenalized(y, x, penal=cls.penalty)
mod.pen_weight *= .5
mod.penal.tau = 0.05
cls.res1 = mod.fit(method='bfgs', maxiter=100, disp=0)
cls.exog_index = slice(None, cls.k_nonzero, None)
cls.atol = 5e-3
def score(
self,
X,
confounder_types,
assignment="assignment",
store_model_fit=False,
intercept=True,
propensity_score_name="propensity score",
):
"""
Fit a propensity score model using the data in X and the confounders listed in confounder_types. This adds
the propensity scores to the dataframe, and returns the new dataframe.
:param X: The data set, with (at least) an assignment, set of confounders, and an outcome
:param assignment: A categorical variable (currently, 0 or 1) indicating test or control group, resp.
:param outcome: The outcome of interest. Should be real-valued or ordinal.
:param confounder_types: A dictionary of variable_name: variable_type pairs of strings, where
variable_type is in {'c', 'o', 'd'}, for 'continuous', 'ordinal', and 'discrete'.
:param store_model_fit: boolean, Whether to store the model as an attribute of the class, as
self.propensity_score_model
:param intercept: Whether to include an intercept in the logistic regression model
:return: A new dataframe with the propensity scores included
"""
df = X[[assignment]].copy()
regression_confounders = []
for confounder, var_type in confounder_types.items():
if var_type == "o" or var_type == "u":
c_dummies = pd.get_dummies(X[[confounder]], prefix=confounder)
if len(c_dummies.columns) == 1:
df = pd.concat([df, c_dummies[c_dummies.columns]], axis=1)
regression_confounders.extend(c_dummies.columns)
else:
df = pd.concat([df, c_dummies[c_dummies.columns[1:]]],
axis=1)
regression_confounders.extend(c_dummies.columns[1:])
else:
regression_confounders.append(confounder)
df.loc[:, confounder] = X[confounder].copy()
df.loc[:, confounder] = X[confounder].copy()
if intercept:
df.loc[:, "intercept"] = 1.0
regression_confounders.append("intercept")
logit = Logit(df[assignment], df[regression_confounders])
model = logit.fit()
if store_model_fit:
self.propensity_score_model = model
X.loc[:, propensity_score_name] = model.predict(
df[regression_confounders])
return X
def regressor(y, X, model_type=model_type):
if model_type == "linear":
regressor = sm.OLS(y, X).fit()
elif model_type == "logistic":
# df = pd.DataFrame({'x':[X], 'y':[y]})
# regressor = sm.logit('y~x', data=df)
regressor = Logit(y, X)
regressor = regressor.fit()
else:
print("\nWrong Model Type : " + model_type +
"\nLinear model type is seleted.")
model_type = "linear"
regressor = sm.OLS(y, X).fit()
return regressor
def test_attack_nocovar(n0, n1, err=.001):
n = n0 + n1
x = [rand.randint(0, 2) for i in range(0, n)]
y = [1 for i in range(0, n)]
for i in range(0, n0):
y[i] = 0
x = AC(x, False)
lr = LR(y, x)
res_lr = lr.fit(disp=0)
OR = math.exp(float(res_lr.params[0]))
ret = attack_no_covar(n0, n1, OR, err)
print "The number of matches is: " + str(len(ret))
print OR
for r in ret:
print r
def _LRT(dependent_var_name: str, independent_var_names: List[str],
study_df: pd.DataFrame) -> Tuple[dict, dict]:
from statsmodels.discrete.discrete_model import Logit
from scipy.linalg import LinAlgError
from statsmodels.tools.sm_exceptions import PerfectSeparationError
from tqdm import tqdm
dic_pvalues = {}
dic_errors = {}
for independent_var_name in tqdm(independent_var_names,
position=0,
leave=True):
print(independent_var_name)
subset_df = study_df.loc[:, [dependent_var_name, independent_var_name]]\
.dropna(how="any")\
.copy()
if subset_df.shape[0] == 0:
dic_pvalues[independent_var_name] = np.NaN
dic_errors[independent_var_name] = "All NaN"
continue
if subset_df[independent_var_name].dtype in ["object", "bool"]:
subset_df = pd.get_dummies(subset_df,
columns=[independent_var_name],
drop_first=False)\
.iloc[:, 0:-1]
y = subset_df[dependent_var_name].cat.codes
X = subset_df.drop(dependent_var_name, axis=1)\
.assign(intercept = 1)
model = Logit(y, X)
try:
results = model.fit(disp=0)
params = results.params.drop("intercept", axis=0)
conf = np.exp(results.conf_int().drop("intercept", axis=0))
conf['OR'] = np.exp(params)
conf["pvalue"] = results.pvalues.drop("intercept", axis=0)
conf = conf.rename({0: 'lb', 1: 'ub'}, axis=1)
dic_or = conf.to_dict(orient="index")
dic_pvalues[independent_var_name] = {
"llr_pvalue": results.llr_pvalue,
**dic_or
}
except (LinAlgError, PerfectSeparationError) as e:
dic_pvalues[independent_var_name] = np.NaN
dic_errors[independent_var_name] = str(e)
return dic_pvalues, dic_errors
class LogReg:
def __init__(self):
self.coef_=None
def fit(self,X,y):
X=add_constant(X)
self.lr=Logit(y,X)
self.l_fitted=self.lr.fit()
self.coef_=self.l_fitted.params[:-1]
def predict(self,X):
if self.coef_ is None:
print('you must first fit the model')
return
X=add_constant(X)
return(self.lr.predict(self.l_fitted.params,X))
def get_logit_results(feature_set,
feature_names,
n,
pos_words,
neg_words,
diff_func=None):
"""
Fit logistic regression to predict pos_words from
neg_words according to the mean difference between
their feature values (up to training month n).
Parameters:
-----------
feature_set : [pandas.DataFrame]
Rows = words, cols = dates.
feature_names : [str]
n : int
pos_words : [str]
neg_words : [str]
diff_func : func(x,y : z)
Compute difference z between vectors x and y.
Returns:
--------
logit_results : statsmodels.discrete.discrete_model.LogitResults
"""
M = len(feature_set)
stats = pd.concat([s.ix[:, 0:n] for s in feature_set], axis=1)
if (diff_func is None):
diff_func = lambda x, y: x - y
X, Y = get_differenced_data(pos_words, neg_words, stats, diff_func)
# mean of differences
X_mean = pd.np.hstack([
pd.np.mean(X.iloc[:, i * n:(i + 1) * n - 1],
axis=1).values.reshape(-1, 1) for i in range(M)
])
X = pd.DataFrame(MinMaxScaler().fit_transform(X_mean),
columns=feature_names)
# remove stats with 0 variance
X = X.ix[:, X.var() > 0.]
X = add_constant(X)
logit = Logit(Y, X)
logit_results = logit.fit()
return logit_results
def attack_no_covar(n0, n1, OR, err=.001):
n = n0 + n1
y = [1 for i in range(0, n)]
for i in range(0, n0):
y[i] = 0
num_match = 0
ret = []
##iterate through all possibilities and test
for i0 in range(0, n0 + 1): ##number in controls with 2 minor alleles
for i1 in range(
0, (n0 - i0 + 1)): ##number in controls with 1 minor alleles
for j0 in range(0, n1 + 1): ##number in cases with 2 minor alleles
for j1 in range(
0,
(n1 - j0 + 1)): ##number in cases with 1 minor alleles
i2 = n0 - i0 - i1
j2 = n1 - j0 - j1
x = [0 for i in range(0, n)]
x[:i0] = [2 for i in range(0, i0)]
cur = i0
x[cur:cur + i1] = [1 for i in range(0, i1)]
cur = cur + i1
cur = cur + i2
x[cur:cur + j0] = [2 for i in range(0, j0)]
cur = cur + j0
x[cur:cur + j1] = [1 for i in range(0, j1)]
res_lr = ""
x = AC(x, False)
lr = LR(y, x)
try:
res_lr = lr.fit(disp=0)
except:
#print x;
continue
try:
OR_cur = math.exp(float(res_lr.params[0]))
except:
continue
if round_sig(OR_cur, err) == round_sig(OR, err):
num_match = num_match + 1
ret.append([i0, i1, i2, j0, j1, j2])
#print "match!\n";
return ret
def simple_model(motif_results_A, non_results_A, motif_results_B,
non_results_B):
all_results = motif_results_A + non_results_A + motif_results_B + non_results_B
is_diplo = np.array([check_is_diplo(result) for result in all_results],
dtype="int")
total_gpc = (len(motif_results_A) + len(non_results_A))
is_gpc = np.zeros(len(all_results), dtype="int")
is_gpc[:total_gpc] = 1
motif = np.zeros(len(all_results), dtype="int")
motif[:len(motif_results_A)] = 1
motif[total_gpc:total_gpc + len(motif_results_B)] = 1
X = np.hstack((np.ones_like(is_gpc)[:, None], is_gpc[:, None],
is_diplo[:, None], (is_gpc * is_diplo)[:, None]))
print(np.sum(X * motif[:, None], axis=0) / np.sum(X, axis=0))
print(np.sum((1 - X) * motif[:, None], axis=0) / np.sum((1 - X), axis=0))
y = motif
model = Logit(y, X)
result = model.fit()
print(result.summary())
def main():
"""
Method to test the implementation
"""
my_log = MyLogisticRegression()
sk_log = LogisticRegression(C=1000)
X = np.random.random((50, 4))
y = np.random.randint(2, size=50)[:, None]
my_log.fit(X, y)
sk_log.fit(X, y)
exog = add_constant(X)
lr = Logit(y, exog)
lrf = lr.fit()
# print(sk_log.coef_, my_log.W, lrf.summary())
assert np.allclose(sk_log.coef_, my_log.W.T, .1), 'incorrect coefs'
def attack(y, cov, OR, err=.001, bnd=.5, numStep=10):
n = n0 + n1
num_match = 0
ret = []
COV = [y]
COV.extend(cov)
COV = np.asarray(COV).T
iter = IterTable(COV)
cur = 0
iter.next()
[yCur, covCur] = iter.get()
while not iter.isDone():
#print cur;
cur = cur + 1
[yCur, covCur] = iter.get()
lr = LR(yCur, AC(covCur, False))
try:
res_lr = lr.fit(disp=0)
except:
iter.next()
continue
OR_cur = 1.0
try:
OR_cur = math.exp(float(res_lr.params[0]))
except:
iter.next()
continue
if abs(OR_cur - OR) < err:
print "match"
num_match = num_match + 1
ret.append(iter.getTable())
#if abs(OR-OR_cur)/OR_cur>bnd:
#for i in range(0,numStep):
#iter.next();
iter.next()
return ret
def logit(df, y_var, X_vars, add_intercept=True):
"""
This function replicates probit in STATA, for probit model.
至少有一个固定效应变量，至多只能有两个。
y变量应为0-1变量。
Inputs.
---------
df:pd.DataFrame, the data for OLS.
y_var:str, the column name of the dependent variable
X_vars:list of str, the list of explanatory variable names
Outputs.
---------
res:obj
"""
new_df = df.copy()
new_df = new_df.dropna()
y = new_df[y_var]
if add_intercept:
new_df['intercept'] = 1.0
X = new_df[['intercept'] + X_vars]
else:
X = new_df[X_vars]
logit_mod = Logit(endog=y, exog=X, check_rank=True, missing="drop")
res = logit_mod.fit(start_params=None,
method='newton',
maxiter=35,
full_output=1,
disp=1,
callback=None)
return res
