Related
What am I doing wrong here? I have tried to see if the shape of ydata and t are the same and they are in fact the same. The only thing that works is when I slice the output of the integrate.odeint function using [:,1] to give me the curve fit of didt. But the thing is, I require all three curves because I plan on graphing all three results. Your help is greatly appreciated.
import pandas as pd
import numpy as np
from datetime import datetime
from scipy import optimize
from scipy import integrate
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
N0=10203134 #susceptible population
ydata=np.array(df_plot.Jordan[253:]) #beginning on 1/10/2020
t=np.arange(len(ydata))
I0=ydata[0] #initial conditions
R0=4821
S0=N0-I0-R0
def SIR_Model(SIR,t,beta,alpha):
S,I,R=SIR
dsdt=-beta*S*I/N0
didt=beta*S*I/N0 -alpha*I
drdt=alpha*I
return dsdt,didt,drdt
def fit_ode(x,beta,alpha):
return integrate.odeint(SIR_Model,(S0,I0,R0),t,args=(beta,alpha))
print(ydata.shape)
print(t.shape)
popt,pcov=optimize.curve_fit(fit_ode,t,ydata)
perr=np.sqrt(np.diag(pcov))
print("standard deviation errors:",str(perr))
print("Optimal Parameters: Beta=",popt[0], "alpha:",popt[1])
ValueError Traceback (most recent call last)
<ipython-input-194-aa1bb286dbba> in <module>
----> 1 popt,pcov=optimize.curve_fit(fit_ode,t,ydata)
2 perr=np.sqrt(np.diag(pcov))
3 print("standard deviation errors:",str(perr))
4 print("Optimal Parameters: Beta=",popt[0], "alpha:",popt[1])
5
C:\ProgramData\Anaconda3\lib\site-packages\scipy\optimize\minpack.py in curve_fit(f, xdata, ydata, p0, sigma, absolute_sigma, check_finite, bounds, method, jac, **kwargs)
782 # Remove full_output from kwargs, otherwise we're passing it in twice.
783 return_full = kwargs.pop('full_output', False)
--> 784 res = leastsq(func, p0, Dfun=jac, full_output=1, **kwargs)
785 popt, pcov, infodict, errmsg, ier = res
786 ysize = len(infodict['fvec'])
C:\ProgramData\Anaconda3\lib\site-packages\scipy\optimize\minpack.py in leastsq(func, x0, args, Dfun, full_output, col_deriv, ftol, xtol, gtol, maxfev, epsfcn, factor, diag)
408 if not isinstance(args, tuple):
409 args = (args,)
--> 410 shape, dtype = _check_func('leastsq', 'func', func, x0, args, n)
411 m = shape[0]
412
C:\ProgramData\Anaconda3\lib\site-packages\scipy\optimize\minpack.py in _check_func(checker, argname, thefunc, x0, args, numinputs, output_shape)
22 def _check_func(checker, argname, thefunc, x0, args, numinputs,
23 output_shape=None):
---> 24 res = atleast_1d(thefunc(*((x0[:numinputs],) + args)))
25 if (output_shape is not None) and (shape(res) != output_shape):
26 if (output_shape[0] != 1):
C:\ProgramData\Anaconda3\lib\site-packages\scipy\optimize\minpack.py in func_wrapped(params)
482 if transform is None:
483 def func_wrapped(params):
--> 484 return func(xdata, *params) - ydata
485 elif transform.ndim == 1:
486 def func_wrapped(params):
ValueError: operands could not be broadcast together with shapes (138,3) (138,)
I want to One-hot-encoding several columns and used several solutions include simple one-hot-encoding, ColumnTransformer, make_column_transformer, Pipeline, and get_dummies but anytime I have got different errors.
x = dataset.iloc[:, :11].values
y = dataset.iloc[:, 11].values
""" data encoding """
from sklearn.preprocessing import LabelEncoder, OneHotEncoder, OrdinalEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
# oe = OrdinalEncoder()
# x = oe.fit_transform(x)
non_cat = ["Make", "Model", "Vehicle", "Transmission", "Fuel"]
onehot_cat = ColumnTransformer([
("categorical", OrdinalEncoder(), non_cat),
("onehot_categorical", OneHotEncoder(), non_cat)],
remainder= "passthrough")
x = onehot_cat.fit_transform(x)
error:
[['ACURA' 'ILX' 'COMPACT' ... 6.7 8.5 33]
['ACURA' 'ILX' 'COMPACT' ... 7.7 9.6 29]
['ACURA' 'ILX HYBRID' 'COMPACT' ... 5.8 5.9 48]
...
['VOLVO' 'XC60 T6 AWD' 'SUV - SMALL' ... 8.6 10.3 27]
['VOLVO' 'XC90 T5 AWD' 'SUV - STANDARD' ... 8.3 9.9 29]
['VOLVO' 'XC90 T6 AWD' 'SUV - STANDARD' ... 8.7 10.7 26]]
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
~\Anaconda3\lib\site-packages\sklearn\utils\__init__.py in _get_column_indices(X, key)
424 try:
--> 425 all_columns = X.columns
426 except AttributeError:
AttributeError: 'numpy.ndarray' object has no attribute 'columns'
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-4-4008371c305f> in <module>
24 ("onehot_categorical", OneHotEncoder(), non_cat)],
25 remainder= "passthrough")
---> 26 x = onehot_cat.fit_transform(x)
27
28 print('OneHotEncode = ', x.shape)
~\Anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in fit_transform(self, X, y)
527 self._validate_transformers()
528 self._validate_column_callables(X)
--> 529 self._validate_remainder(X)
530
531 result = self._fit_transform(X, y, _fit_transform_one)
~\Anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py in _validate_remainder(self, X)
325 cols = []
326 for columns in self._columns:
--> 327 cols.extend(_get_column_indices(X, columns))
328
329 remaining_idx = sorted(set(range(self._n_features)) - set(cols))
~\Anaconda3\lib\site-packages\sklearn\utils\__init__.py in _get_column_indices(X, key)
425 all_columns = X.columns
426 except AttributeError:
--> 427 raise ValueError("Specifying the columns using strings is only "
428 "supported for pandas DataFrames")
429 if isinstance(key, str):
ValueError: Specifying the columns using strings is only supported for pandas DataFrames
I got a similar error trying to make prediction using a model. It was expecting a dataframe but I was sending a numpy object instead. So I changed it from:
prediction = monitor_model.predict(s_df.to_numpy())
to:
prediction = monitor_model.predict(s_df)
I m new to data science and python, and jupyter notebook, I m currently studying how to do k means clustering on a data set. I came across ways in which can introduce data
Data = {'x': [25,34,22,27,33,33,31,22,35,34,67,54,57,43,50,57,59,52,65,47,49,48,35,33,44,45,38,43,51,46],
'y': [79,51,53,78,59,74,73,57,69,75,51,32,40,47,53,36,35,58,59,50,25,20,14,12,20,5,29,27,8,7]
}
df = DataFrame(Data,columns=['x','y'])
and use of blobs
data = make_blobs(n_samples=200, n_features=2, centers=4, cluster_std=1.6, random_state=50)
but I would like to know how to do a proper code with a csv file imported from my computer and do a k means with scaling, thank you in advance, I could not find relevant blogs to help me
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set()
from sklearn.cluster import KMeans
data=pd.read_csv("C:/Users/Dulangi/Downloads/winequality-red.csv")
data
data["alcohol"]=data["alcohol"]/data["alcohol"].max()
data["quality"]=data["quality"]/data["quality"].max()
plt.scatter(data["alcohol"],data['quality'])
plt.xlabel("alcohol")
plt.ylabel('quality')
plt.show()
x=data.copy()
kmeans=KMeans(2)
kmeans.fit(x)
clusters=x.copy()
clusters['cluster_pred']=kmeans.fit_predict(x)
plt.scatter(clusters["alcohol"],clusters['quality'],c=clusters['cluster_pred'],cmap='rainbow')
plt.xlabel("alcohol")
plt.ylabel('quality')
plt.show()
from sklearn import preprocessing
x_scaled=preprocessing.scale(x)
#x_scaled
wcss=[]
for i in range(1,30):
kmeans=KMeans(i)
kmeans.fit(x_scaled)
wcss.append(kmeans.inertia_)
wcss
plt.plot(range(1,30),wcss)
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()
This is what i tried
the error i got
ValueError Traceback (most recent call last)
<ipython-input-12-d4955ce8615e> in <module>
39
40
---> 41 plt.plot(range(1,30),wcss)
42 plt.xlabel('Number of clusters')
43 plt.ylabel('WCSS')
~\Anaconda3\lib\site-packages\matplotlib\pyplot.py in plot(scalex, scaley, data, *args, **kwargs)
2787 return gca().plot(
2788 *args, scalex=scalex, scaley=scaley, **({"data": data} if data
-> 2789 is not None else {}), **kwargs)
2790
2791
~\Anaconda3\lib\site-packages\matplotlib\axes\_axes.py in plot(self, scalex, scaley, data, *args, **kwargs)
1664 """
1665 kwargs = cbook.normalize_kwargs(kwargs, mlines.Line2D._alias_map)
-> 1666 lines = [*self._get_lines(*args, data=data, **kwargs)]
1667 for line in lines:
1668 self.add_line(line)
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in __call__(self, *args, **kwargs)
223 this += args[0],
224 args = args[1:]
--> 225 yield from self._plot_args(this, kwargs)
226
227 def get_next_color(self):
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in _plot_args(self, tup, kwargs)
389 x, y = index_of(tup[-1])
390
--> 391 x, y = self._xy_from_xy(x, y)
392
393 if self.command == 'plot':
~\Anaconda3\lib\site-packages\matplotlib\axes\_base.py in _xy_from_xy(self, x, y)
268 if x.shape[0] != y.shape[0]:
269 raise ValueError("x and y must have same first dimension, but "
--> 270 "have shapes {} and {}".format(x.shape, y.shape))
271 if x.ndim > 2 or y.ndim > 2:
272 raise ValueError("x and y can be no greater than 2-D, but have "
ValueError: x and y must have same first dimension, but have shapes (29,) and (1,)
You can easily do by using scikit-Learn
import pandas as pd
data=pd.read_csv('myfile.csv')
df=pd.DataFrame(data,index=None)
df.head()
Check if rows contain any null values
df.isnull().sum()
Drop all the rows with null values if any
df_numeric.dropna(inplace=True)
Normalize data
Normalize the data with MinMax scaling provided by sklearn
from sklearn import preprocessing
minmax_processed = preprocessing.MinMaxScaler().fit_transform(df.drop('title',axis=1))
df_numeric_scaled = pd.DataFrame(minmax_processed, index=df.index, columns=df.columns[:-1])
df_numeric_scaled.head()
from sklearn.cluster import KMeans
Apply K-Means Clustering
What k to choose?
Let's fit cluster size 1 to 20 on our data and take a look at the corresponding score value.
Nc = range(1, 20)
kmeans = [KMeans(n_clusters=i) for i in Nc]
score = [kmeans[i].fit(df_numeric_scaled).score(df_numeric_scaled) for i in range(len(kmeans))]
These score values signify how far our observations are from the cluster center. We want to keep this score value around 0. A large positive or a large negative value would indicate that the cluster center is far from the observations.
Based on these scores value, we plot an Elbow curve to decide which cluster size is optimal. Note that we are dealing with tradeoff between cluster size(hence the computation required) and the relative accuracy.
import matplotlib as pl
pl.plot(Nc,score)
pl.xlabel('Number of Clusters')
pl.ylabel('Score')
pl.title('Elbow Curve')
pl.show()
Fit K-Means for clustering with k=5
kmeans = KMeans(n_clusters=5)
kmeans.fit(df_numeric_scaled)
df['cluster'] = kmeans.labels_
df.head()
I am using a while loop to calculate a cost function for memory reasons. When calculating the gradient, tensorflow will store Nm tensors where Nm is the number of iterations in my while loop (this cuases the same memory issues I had with the original energy functions). I do not want that as I don't have enough memory. So I want to register a new op along with a gradient function that both use a while loop. However I am having issues with using function.defun and a while loop. To simplify things, I have a small test example below:
import numpy as np
import tensorflow as tf
from tensorflow.python.framework import ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import sparse_ops
from tensorflow.python.framework import function
def _run(tensor):
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
res = sess.run(tensor)
return res
#function.Defun(tf.float32,tf.float32,func_name ='tf_test_log')#,grad_func=tf_test_logGrad)
def tf_test_log(t_x,t_y):
#N = t_x.shape[0].value
condition = lambda i,m1: i<N
def body(index,x):
#return[(index+1),tf.concat([x, tf.expand_dims(tf.exp( tf.add( t_x[:,index],t_y[:,index]) ),1) ],1 ) ]
return[(index+1),tf.add(x, tf.exp( tf.add( t_x[:,0],t_y[:,0]) ) ) ]
i0 = tf.constant(0,dtype=tf.int32)
m0 = tf.zeros([N,1],dType)
ijk_0 = [i0,m0]
L,t_log_x = tf.while_loop(condition,body,ijk_0,
shape_invariants=[i0.get_shape(),
tf.TensorShape([N,None])]
)
return t_log_x
dType = tf.float32
N = np.int32(100)
t_N = tf.constant(N,dtype = tf.int32)
t_x = tf.constant(np.random.randn(N,N),dtype = dType)
t_y = tf.constant(np.random.randn(N,N),dtype = dType)
ys = _run(tf_test_log(t_x,t_y))
I then try to test the new op:
I get a Value error: The shape for while/Merge_1:0 is not an invariant for the loop. It enters the loop with shape (100, ?), but has shape after one iteration. Provide shape invariants using either the shape_invariants argument of tf.while_loop or set_shape() on the loop variables.
Note that calling
If i use a concatenate operation (instead of the add operation that gets returned by my while loop), I do not get any issues.
However, If I do not set N as a global variable (i.e. I do N = t_x.shape[0]) inside the body of the tf_test_log function, I get a Value error.
ValueError: Cannot convert a partially known TensorShape to a Tensor: (?, 1)
What is wrong with my code? Any help is greatly appreciated!
I am using python 3.5 on ubuntu 16.04 and tensorflow 1.4
full output:
ValueError Traceback (most recent call last)
~/Documents/TheEffingPhDHatersGonnaHate/PAM/defun_while.py in <module>()
51 t_x = tf.constant(np.random.randn(N,N),dtype = dType)
52 t_y = tf.constant(np.random.randn(N,N),dtype = dType)
---> 53 ys = _run(tf_test_log(t_x,t_y))
54
55
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in __call__(self, *args, **kwargs)
503
504 def __call__(self, *args, **kwargs):
--> 505 self.add_to_graph(ops.get_default_graph())
506 args = [ops.convert_to_tensor(_) for _ in args] + self._extra_inputs
507 ret, op = _call(self._signature, *args, **kwargs)
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in add_to_graph(self, g)
484 def add_to_graph(self, g):
485 """Adds this function into the graph g."""
--> 486 self._create_definition_if_needed()
487
488 # Adds this function into 'g'.
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in _create_definition_if_needed(self)
319 """Creates the function definition if it's not created yet."""
320 with context.graph_mode():
--> 321 self._create_definition_if_needed_impl()
322
323 def _create_definition_if_needed_impl(self):
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in _create_definition_if_needed_impl(self)
336 # Call func and gather the output tensors.
337 with vs.variable_scope("", custom_getter=temp_graph.getvar):
--> 338 outputs = self._func(*inputs)
339
340 # There is no way of distinguishing between a function not returning
~/Documents/TheEffingPhDHatersGonnaHate/PAM/defun_while.py in tf_test_log(t_x, t_y)
39 L,t_log_x = tf.while_loop(condition,body,ijk_0,
40 shape_invariants=[i0.get_shape(),
---> 41 tf.TensorShape([N,None])]
42 )
43 return t_log_x
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in while_loop(cond, body, loop_vars, shape_invariants, parallel_iterations, back_prop, swap_memory, name)
2814 loop_context = WhileContext(parallel_iterations, back_prop, swap_memory) # pylint: disable=redefined-outer-name
2815 ops.add_to_collection(ops.GraphKeys.WHILE_CONTEXT, loop_context)
-> 2816 result = loop_context.BuildLoop(cond, body, loop_vars, shape_invariants)
2817 return result
2818
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in BuildLoop(self, pred, body, loop_vars, shape_invariants)
2638 self.Enter()
2639 original_body_result, exit_vars = self._BuildLoop(
-> 2640 pred, body, original_loop_vars, loop_vars, shape_invariants)
2641 finally:
2642 self.Exit()
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in _BuildLoop(self, pred, body, original_loop_vars, loop_vars, shape_invariants)
2619 for m_var, n_var in zip(merge_vars, next_vars):
2620 if isinstance(m_var, ops.Tensor):
-> 2621 _EnforceShapeInvariant(m_var, n_var)
2622
2623 # Exit the loop.
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/control_flow_ops.py in _EnforceShapeInvariant(merge_var, next_var)
576 "Provide shape invariants using either the `shape_invariants` "
577 "argument of tf.while_loop or set_shape() on the loop variables."
--> 578 % (merge_var.name, m_shape, n_shape))
579 else:
580 if not isinstance(var, (ops.IndexedSlices, sparse_tensor.SparseTensor)):
ValueError: The shape for while/Merge_1:0 is not an invariant for the loop. It enters the loop with shape (100, ?), but has shape <unknown> after one iteration. Provide shape invariants using either the `shape_invariants` argument of tf.while_loop or set_shape() on the loop variables.
Thanks #Alexandre Passos for the suggestion in the comment above!
The following piece of code is a modification of the original with a set_shape function added inside the body.
import numpy as np
import tensorflow as tf
from tensorflow.python.framework import ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import sparse_ops
from tensorflow.python.framework import function
def _run(tensor):
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
res = sess.run(tensor)
return res
#function.Defun(tf.float32,tf.float32,tf.float32,func_name ='tf_test_logGrad')
def tf_test_logGrad(t_x,t_y,grad):
return grad
#function.Defun(tf.float32,tf.float32,func_name ='tf_test_log')#,grad_func=tf_test_logGrad)
def tf_test_log(t_x,t_y):
#N = t_x.shape[0].value
condition = lambda i,m1: i<N
def body(index,x):
#return[(index+1),tf.concat([x, tf.expand_dims(tf.exp( tf.add( t_x[:,index],t_y[:,index]) ),1) ],1 ) ]
x = tf.add(x, tf.exp( tf.add( t_x[:,0],t_y[:,0]) ) )
x.set_shape([N])
return[(index+1), x]
i0 = tf.constant(0,dtype=tf.int32)
m0 = tf.zeros([N],dType)
ijk_0 = [i0,m0]
L,t_log_x = tf.while_loop(condition,body,ijk_0,
shape_invariants=[i0.get_shape(),
tf.TensorShape([N])]
)
return t_log_x
dType = tf.float32
N = np.int32(100)
t_N = tf.constant(N,dtype = tf.int32)
t_x = tf.constant(np.random.randn(N,N),dtype = dType)
t_y = tf.constant(np.random.randn(N,N),dtype = dType)
ys = _run(tf_test_log(t_x,t_y))
The Issue of global N still persists.
You still need to set the shape of the loop tensors as a global variable outside of the defun decorator. If you try to get it from the shape of the inputs of the defun decorator, you get:
TypeError Traceback (most recent call last)
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py in zeros(shape, dtype, name)
1438 shape = tensor_shape.as_shape(shape)
-> 1439 output = constant(zero, shape=shape, dtype=dtype, name=name)
1440 except (TypeError, ValueError):
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name, verify_shape)
207 tensor_util.make_tensor_proto(
--> 208 value, dtype=dtype, shape=shape, verify_shape=verify_shape))
209 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape)
379 # exception when dtype is set to np.int64
--> 380 if shape is not None and np.prod(shape, dtype=np.int64) == 0:
381 nparray = np.empty(shape, dtype=np_dt)
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/numpy/core/fromnumeric.py in prod(a, axis, dtype, out, keepdims)
2517 return _methods._prod(a, axis=axis, dtype=dtype,
-> 2518 out=out, **kwargs)
2519
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/numpy/core/_methods.py in _prod(a, axis, dtype, out, keepdims)
34 def _prod(a, axis=None, dtype=None, out=None, keepdims=False):
---> 35 return umr_prod(a, axis, dtype, out, keepdims)
36
TypeError: __int__ returned non-int (type NoneType)
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
~/Documents/TheEffingPhDHatersGonnaHate/PAM/defun_while.py in <module>()
52 t_x = tf.constant(np.random.randn(N,N),dtype = dType)
53 t_y = tf.constant(np.random.randn(N,N),dtype = dType)
---> 54 ys = _run(tf_test_log(t_x,t_y))
55
56
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in __call__(self, *args, **kwargs)
503
504 def __call__(self, *args, **kwargs):
--> 505 self.add_to_graph(ops.get_default_graph())
506 args = [ops.convert_to_tensor(_) for _ in args] + self._extra_inputs
507 ret, op = _call(self._signature, *args, **kwargs)
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in add_to_graph(self, g)
484 def add_to_graph(self, g):
485 """Adds this function into the graph g."""
--> 486 self._create_definition_if_needed()
487
488 # Adds this function into 'g'.
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in _create_definition_if_needed(self)
319 """Creates the function definition if it's not created yet."""
320 with context.graph_mode():
--> 321 self._create_definition_if_needed_impl()
322
323 def _create_definition_if_needed_impl(self):
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/function.py in _create_definition_if_needed_impl(self)
336 # Call func and gather the output tensors.
337 with vs.variable_scope("", custom_getter=temp_graph.getvar):
--> 338 outputs = self._func(*inputs)
339
340 # There is no way of distinguishing between a function not returning
~/Documents/TheEffingPhDHatersGonnaHate/PAM/defun_while.py in tf_test_log(t_x, t_y)
33
34 i0 = tf.constant(0,dtype=tf.int32)
---> 35 m0 = tf.zeros([N],dType)
36
37
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py in zeros(shape, dtype, name)
1439 output = constant(zero, shape=shape, dtype=dtype, name=name)
1440 except (TypeError, ValueError):
-> 1441 shape = ops.convert_to_tensor(shape, dtype=dtypes.int32, name="shape")
1442 output = fill(shape, constant(zero, dtype=dtype), name=name)
1443 assert output.dtype.base_dtype == dtype
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, preferred_dtype)
834 name=name,
835 preferred_dtype=preferred_dtype,
--> 836 as_ref=False)
837
838
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
924
925 if ret is None:
--> 926 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
927
928 if ret is NotImplemented:
~/environments/tf_1_4_gpu/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py in _tensor_shape_tensor_conversion_function(s, dtype, name, as_ref)
248 if not s.is_fully_defined():
249 raise ValueError(
--> 250 "Cannot convert a partially known TensorShape to a Tensor: %s" % s)
251 s_list = s.as_list()
252 int64_value = 0
ValueError: Cannot convert a partially known TensorShape to a Tensor: (?,)
I'm trying to do a weighted Ridge Regression with sklearn. However, the code breaks when I call the fit method. The exception I get is :
Exception: Data must be 1-dimensional
But I'm sure (by checking through print-statements) that the data I'm passing has the right shapes.
print temp1.shape #(781, 21)
print temp2.shape #(781,)
print weights.shape #(781,)
result=RidgeCV(normalize=True).fit(temp1,temp2,sample_weight=weights)
What could be going wrong ??
Here's the whole output :
---------------------------------------------------------------------------
Exception Traceback (most recent call last)
<ipython-input-65-a5b1eba5d9cf> in <module>()
22
23
---> 24 result=RidgeCV(normalize=True).fit(temp2,temp1, sample_weight=weights)
25
26
/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/ridge.pyc in fit(self, X, y, sample_weight)
868 gcv_mode=self.gcv_mode,
869 store_cv_values=self.store_cv_values)
--> 870 estimator.fit(X, y, sample_weight=sample_weight)
871 self.alpha_ = estimator.alpha_
872 if self.store_cv_values:
/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/ridge.pyc in fit(self, X, y, sample_weight)
793 else alpha)
794 if error:
--> 795 out, c = _errors(weighted_alpha, y, v, Q, QT_y)
796 else:
797 out, c = _values(weighted_alpha, y, v, Q, QT_y)
/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/ridge.pyc in _errors(self, alpha, y, v, Q, QT_y)
685 w = 1.0 / (v + alpha)
686 c = np.dot(Q, self._diag_dot(w, QT_y))
--> 687 G_diag = self._decomp_diag(w, Q)
688 # handle case where y is 2-d
689 if len(y.shape) != 1:
/usr/local/lib/python2.7/dist-packages/sklearn/linear_model/ridge.pyc in _decomp_diag(self, v_prime, Q)
672 def _decomp_diag(self, v_prime, Q):
673 # compute diagonal of the matrix: dot(Q, dot(diag(v_prime), Q^T))
--> 674 return (v_prime * Q ** 2).sum(axis=-1)
675
676 def _diag_dot(self, D, B):
/usr/local/lib/python2.7/dist-packages/pandas/core/ops.pyc in wrapper(left, right, name)
531 return left._constructor(wrap_results(na_op(lvalues, rvalues)),
532 index=left.index, name=left.name,
--> 533 dtype=dtype)
534 return wrapper
535
/usr/local/lib/python2.7/dist-packages/pandas/core/series.pyc in __init__(self, data, index, dtype, name, copy, fastpath)
209 else:
210 data = _sanitize_array(data, index, dtype, copy,
--> 211 raise_cast_failure=True)
212
213 data = SingleBlockManager(data, index, fastpath=True)
/usr/local/lib/python2.7/dist-packages/pandas/core/series.pyc in _sanitize_array(data, index, dtype, copy, raise_cast_failure)
2683 elif subarr.ndim > 1:
2684 if isinstance(data, np.ndarray):
-> 2685 raise Exception('Data must be 1-dimensional')
2686 else:
2687 subarr = _asarray_tuplesafe(data, dtype=dtype)
Exception: Data must be 1-dimensional
The error seems to be due to sample_weights being a Pandas series rather than a numpy array:
from sklearn.linear_model import RidgeCV
temp1 = pd.DataFrame(np.random.rand(781, 21))
temp2 = pd.Series(temp1.sum(1))
weights = pd.Series(1 + 0.1 * np.random.rand(781))
result = RidgeCV(normalize=True).fit(temp1, temp2,
sample_weight=weights)
# Exception: Data must be 1-dimensional
If you use a numpy array instead, the error goes away:
result = RidgeCV(normalize=True).fit(temp1, temp2,
sample_weight=weights.values)
This seems to be a bug; I've opened a scikit-learn issue to report this.