Merge pull request #83 from cosanlab/fixVisualization

Plotting, analyses, tutorials, and requirement fixes.

README.md

@@ -1,7 +1,6 @@
 # Py-FEAT  
 [![Build Status](https://api.travis-ci.org/cosanlab/feat.svg?branch=master)](https://travis-ci.org/cosanlab/feat/)
-[![Coverage Status](https://coveralls.io/repos/github/cosanlab/feat/badge.svg?branch=master)](https://coveralls.io/github/cosanlab/feat?branch=master)
-
+[![Coverage Status](https://coveralls.io/repos/github/cosanlab/py-feat/badge.svg?branch=master)](https://coveralls.io/github/cosanlab/py-feat?branch=master)
 Python Facial Expression Analysis Toolbox (FEAT)
 
 Py-FEAT is a suite for facial expressions (FEX) research written in Python. This package includes tools to detect faces, extract emotional facial expressions (e.g., happiness, sadness, anger), facial muscle movements (e.g., action units), and facial landmarks, from videos and images of faces, as well as methods to preprocess, analyze, and visualize FEX data. 

feat/data.py

@@ -7,8 +7,6 @@
 import numpy as np
 import pandas as pd
 from pandas import DataFrame, Series, Index
-import six
-import abc
 from copy import deepcopy
 from functools import reduce
 from nltools.data import Adjacency, design_matrix
@@ -31,7 +29,7 @@
 from feat.plotting import plot_face, draw_lineface, draw_muscles
 from nilearn.signal import clean
 from scipy.signal import convolve
-from scipy.stats import ttest_1samp
+from scipy.stats import ttest_1samp, ttest_ind
 
 
 class FexSeries(Series):
@@ -689,7 +687,7 @@ def regress(self, X, y, fit_intercept=True, *args, **kwargs):
         res_df = pd.DataFrame(res, columns=my.columns)
         return b_df, t_df, p_df, df_df, res_df
 
-    def ttest(self, popmean=0, threshold_dict=None):
+    def ttest_1samp(self, popmean=0, threshold_dict=None):
         """Conducts 1 sample ttest.
 
         Uses scipy.stats.ttest_1samp to conduct 1 sample ttest
@@ -703,6 +701,24 @@ def ttest(self, popmean=0, threshold_dict=None):
         """
         return ttest_1samp(self, popmean)
 
+    def ttest_ind(self, col, sessions, threshold_dict=None):
+        """Conducts 2 sample ttest.
+
+        Uses scipy.stats.ttest_ind to conduct 2 sample ttest on column col between sessions.
+
+        Args:
+            col (str): Column names to compare in a t-test between sessions
+            session_names (tuple): tuple of session names stored in Fex.sessions.
+            threshold_dict ([type], optional): Dictonary for thresholding. Defaults to None. [NOT IMPLEMENTED]
+
+        Returns:
+            t, p: t-statistics and p-values
+        """
+        sess1, sess2 = sessions
+        a = self[self.sessions == sess1][col]
+        b = self[self.sessions == sess2][col]
+        return ttest_ind(a, b)
+
     def predict(self, X, y, model=LinearRegression, *args, **kwargs):
         """Predicts y from X using a sklearn model.
 
@@ -755,6 +771,25 @@ def downsample(self, target, **kwargs):
         return df_ds
         # return self.__class__(df_ds, sampling_freq=target, features=ds_features)
 
+    def isc(self, col, index="frame", columns="input", method="pearson"):   
+        """[summary]
+
+        Args:
+            col (str]): Column name to compute the ISC for.
+            index (str, optional): Column to be used in computing ISC. Usually this would be the column identifying the time such as the number of the frame. Defaults to "frame".
+            columns (str, optional): Column to be used for ISC. Usually this would be the column identifying the video or subject. Defaults to "input".
+            method (str, optional): Method to use for correlation pearson, kendall, or spearman. Defaults to "pearson".
+
+        Returns:
+            DataFrame: Correlation matrix with index as colmns 
+        """                 
+        if index == None:
+            index = 'frame'
+        if columns == None:
+            columns = "input"
+        mat = pd.pivot_table(self, index = index, columns=columns, values=col).corr(method=method)
+        return mat 
+
     def upsample(self, target, target_type="hz", **kwargs):
         """Upsample Fex columns. Relies on nltools.stats.upsample,
             but ensures that returned object is a Fex object.

feat/plotting.py

@@ -863,7 +863,7 @@ def plot_face(
 
     Args:
         model: sklearn PLSRegression instance
-        au: vector of action units (same length as model.x_mean_)
+        au: vector of action units (same length as model.n_components)
         vectorfield: (dict) {'target':target_array,'reference':reference_array}
         muscles: (dict) {'muscle': color}
         ax: matplotlib axis handle
@@ -883,7 +883,7 @@ def plot_face(
             raise ValueError("make sure that model is a PLSRegression instance")
 
     if au is None:
-        au = np.zeros(len(model.x_mean_))
+        au = np.zeros(model.n_components)
         warnings.warn(
             "Don't forget to pass an 'au' vector of len(20), "
             "using neutral as default"
@@ -927,7 +927,7 @@ def plot_face(
             vectorfield["target"] = landmarks
         draw_vectorfield(ax=ax, **vectorfield)
     ax.set_xlim([25, 172])
-    ax.set_ylim((-240, -50))
+    ax.set_ylim((240, 50))
     ax.axes.get_xaxis().set_visible(False)
     ax.axes.get_yaxis().set_visible(False)
     return ax
@@ -948,20 +948,20 @@ def predict(au, model=None):
     elif not isinstance(model, PLSRegression):
         raise ValueError("make sure that model is a PLSRegression instance")
 
-    if len(au) != len(model.x_mean_):
+    if len(au) != model.n_components:
         print(au)
-        print(len(model.x_mean_))
-        raise ValueError("au vector must be len(", len(model.x_mean_), ").")
+        print(model.n_components)
+        raise ValueError("au vector must be len(", model.n_components, ").")
 
     if len(au.shape) == 1:
         au = np.reshape(au, (1, -1))
 
     landmarks = np.reshape(model.predict(au), (2, 68))
-    landmarks[1, :] = -1 * landmarks[1, :]  # this might not generalize to other models
+    # landmarks[1, :] = -1 * landmarks[1, :]  # this might not generalize to other models
     return landmarks
 
 
-def _create_empty_figure(figsize=(4, 5), xlim=[25, 172], ylim=[-240, -50]):
+def _create_empty_figure(figsize=(4, 5), xlim=[25, 172], ylim=[240, 50]):
     """Create an empty figure"""
     plt.figure(figsize=figsize)
     ax = plt.gca()

feat/tests/test_feat.py

@@ -410,5 +410,15 @@ def test_stats():
     clf = openface.predict(X = openface[["AU02_c"]], y = openface["AU04_c"])
     assert clf.coef_ < 0
 
-    t, p = openface[["AU02_c"]].ttest()
-    assert t > 0
+    t, p = openface[["AU02_c"]].ttest_1samp()
+    assert t > 0
+
+    a = openface.aus().assign(input = "0")
+    b = openface.aus().apply(lambda x: x+np.random.rand(100)).assign(input = "1")
+    doubled = pd.concat([a, b])
+    doubled.sessions = doubled['input']
+    t, p = doubled.ttest_ind(col="AU12_r", sessions = ("0", "1"))
+    assert(t < 0)
+
+    frame = np.concatenate([np.array(range(int(len(doubled)/2))), np.array(range(int(len(doubled)/2)))])
+    assert(doubled.assign(frame = frame).isc(col = "AU04_r").iloc[0,0] == 1)

feat/tests/test_plot.py

@@ -13,7 +13,7 @@
 
 
 def assert_plot_shape(ax):
-    assert ax.get_ylim() == (-240.0, -50.0)
+    assert ax.get_ylim() == (240.0, 50.0)
     assert ax.get_xlim() == (25.0, 172.0)
 
 

feat/tests/test_utils.py

@@ -17,7 +17,6 @@
     neutral,
     softmax,
     load_h5,
-    load_pickled_model,
 )
 from nltools.data import Adjacency
 import unittest
@@ -47,9 +46,4 @@ def test_utils():
     assert softmax(0) == 0.5
     # Test badfile.
     with pytest.raises(Exception):
-        load_h5("badfile.h5")
-
-    # Test loading of pickled model
-    out = load_pickled_model()
-    with pytest.raises(Exception):
-        load_pickled_model("badfile.pkl")
+        load_h5("badfile.h5")

feat/utils.py

@@ -12,7 +12,6 @@
 
 __all__ = [
     "get_resource_path",
-    "load_pickled_model",
     "read_facet",
     "read_affdex",
     "read_affectiva",
@@ -27,6 +26,10 @@
 
 import os, math, pywt, pickle, h5py
 from sklearn.cross_decomposition import PLSRegression
+# setattr(PLSRegression, "_x_mean", None)
+# setattr(PLSRegression, "_y_mean", None)
+# setattr(PLSRegression, "_x_std", None)
+from sklearn import __version__
 import numpy as np, pandas as pd
 from scipy import signal
 from scipy.integrate import simps
@@ -197,30 +200,7 @@ def get_resource_path():
     # return ("F:/feat/feat/") # points to the package folder.
     # return os.path.join(os.path.dirname(__file__), 'resources')
 
-
-def load_pickled_model(file_name="pls_python27.pkl"):
-    """Load the pickled PLS model for plotting.
-
-    Args:
-        file_name ([type], optional): Specify model to load. Defaults to  pls_python27.pkl.
-
-    Returns:
-        model: PLS model
-    """
-    file_name = os.path.join(get_resource_path(), file_name)
-    try:
-        with open(file_name, "rb") as f:
-            model = pickle.load(f)
-    except UnicodeDecodeError as e:
-        with open(file_name, "rb") as f:
-            model = pickle.load(f, encoding="latin1")
-    except Exception as e:
-        print("Unable to load data ", file_name, ":", e)
-        raise
-    return model
-
-
-def load_h5(file_name="blue.h5"):
+def load_h5(file_name="pyfeat_aus_to_landmarks.h5"):
     """Load the h5 PLS model for plotting.
 
     Args:
@@ -237,9 +217,14 @@ def load_h5(file_name="blue.h5"):
         d4 = hf.get("x_std")
         model = PLSRegression(len(d1))
         model.coef_ = np.array(d1)
-        model.x_mean_ = np.array(d2)
-        model.y_mean_ = np.array(d3)
-        model.x_std_ = np.array(d4)
+        if int(__version__.split(".")[1]) < 24:
+            model.x_mean_ = np.array(d2)
+            model.y_mean_ = np.array(d3)
+            model.x_std_ = np.array(d4)
+        else:
+            model._x_mean = np.array(d2)
+            model._y_mean = np.array(d3)
+            model._x_std = np.array(d4)
         hf.close()
     except Exception as e:
         print("Unable to load data ", file_name, ":", e)

feat/version.py

@@ -1 +1 @@
-__version__ = '0.3.3'
+__version__ = '0.3.5'

notebooks/_build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 448bfbd75a7fd9759e78e402a6653eab
+config: a5b64bda98e84dd45786b2d9d4c3d7e5
 tags: 645f666f9bcd5a90fca523b33c5a78b7