Merge 173f8c1 into 242050a

biocore · Mar 8, 2019 · e87481b · e87481b
2 parents 242050a + 173f8c1
commit e87481b
Show file tree

Hide file tree

Showing 12 changed files with 65 additions and 9 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,45 @@
+# DEICODE changelog
+
+## Version 0.1.6 (2019-3-8)
+
+In PR#27
+
+### Features
+
+### Backward-incompatible changes [stable]
+
+### Backward-incompatible changes [experimental]
+
+### Performance enhancements
+
+### Bug fixes
+
+* Centered the feature and sample loadings for biplot visualization (issue #26).
+
+### Deprecated functionality [stable]
+
+### Deprecated functionality [experimental]
+
+### Miscellaneous
+
+* Fixed the broken image links.
+
+## Version 0.1.5
+
+Original "working" code
+
+### Features
+
+### Backward-incompatible changes [stable]
+
+### Backward-incompatible changes [experimental]
+
+### Performance enhancements
+
+### Bug fixes
+
+### Deprecated functionality [stable]
+
+### Deprecated functionality [experimental]
+
+### Miscellaneous
diff --git a/deicode/__init__.py b/deicode/__init__.py
@@ -8,4 +8,4 @@
 #
 # ----------------------------------------------------------------------------
 
-__version__ = "0.1.5"
+__version__ = "0.1.6"
diff --git a/deicode/q2/_method.py b/deicode/q2/_method.py
@@ -32,10 +32,12 @@ def sample_filter(val, id_, md): return sum(val) > min_sample_count
     feature_loading = pd.DataFrame(opt.feature_weights, index=table.columns)
     feature_loading = feature_loading.rename(columns=rename_cols)
     feature_loading.sort_values('PC1', inplace=True, ascending=True)
+    feature_loading -= feature_loading.mean(axis=0)
 
     # Sample Loadings
     sample_loading = pd.DataFrame(opt.sample_weights, index=table.index)
     sample_loading = sample_loading.rename(columns=rename_cols)
+    sample_loading -= sample_loading.mean(axis=0)
 
     # % var explained
     proportion_explained = pd.Series(opt.explained_variance_ratio,

diff --git a/deicode/scripts/_rpca.py b/deicode/scripts/_rpca.py
@@ -38,10 +38,12 @@ def sample_filter(val, id_, md): return sum(val) > min_sample_depth
     feature_loading = pd.DataFrame(opt.feature_weights, index=table.columns)
     feature_loading = feature_loading.rename(columns=rename_cols)
     feature_loading.sort_values('PC1', inplace=True, ascending=True)
+    feature_loading -= feature_loading.mean(axis=0)
 
     # Sample Loadings
     sample_loading = pd.DataFrame(opt.sample_weights, index=table.index)
     sample_loading = sample_loading.rename(columns=rename_cols)
+    sample_loading -= sample_loading.mean(axis=0)
 
     proportion_explained = pd.Series(opt.explained_variance_ratio,
                                      index=list(rename_cols.values()))

diff --git a/ipynb/tutorials/etc/img8.png b/ipynb/tutorials/etc/img8.png
diff --git a/ipynb/tutorials/etc/img9.png b/ipynb/tutorials/etc/img9.png
diff --git a/ipynb/tutorials/moving-pictures.ipynb b/ipynb/tutorials/moving-pictures.ipynb
@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -104,7 +104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
@@ -135,7 +135,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -161,14 +161,14 @@
    "source": [
     "Biplots are exploratory visualization tools that allow us to represent the features (i.e. taxonomy or OTUs)  that strongly influence the principal component axis as arrows. The interpretation of the compositional biplot differs slightly from classical biplot interpretation (we can view the qzv file at [view.qiime2](https://view.qiime2.org). The important features with regard to sample clusters are not a single arrow but by the log ratio between features represented by arrows pointing in different directions. A visualization tool for these log ratios is coming soon to QIIME. \n",
     "\n",
-    "![](http://i66.tinypic.com/28rm5pj.png)\n",
+    "![](etc/img8.png)\n",
     "\n",
     "From this visualization we noticed that BodySite seems to explain the clusters well. We can run [PERMANOVA](https://docs.qiime2.org/2019.1/plugins/available/diversity/beta-group-significance/) on the distances to get a statistical significance for this. "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -194,8 +194,15 @@
    "source": [
     "Indeed we can now see that the clusters we saw in the biplot were significant by viewing the BodySite_significance.qzv at [view.qiime2](https://view.qiime2.org).\n",
     "\n",
-    "![](http://i66.tinypic.com/vy6y6c.jpg)"
+    "![](etc/img9.png)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

diff --git a/ipynb/tutorials/moving-pictures.md b/ipynb/tutorials/moving-pictures.md
@@ -116,7 +116,7 @@ qiime emperor biplot \
 
 Biplots are exploratory visualization tools that allow us to represent the features (i.e. taxonomy or OTUs)  that strongly influence the principal component axis as arrows. The interpretation of the compositional biplot differs slightly from classical biplot interpretation (we can view the qzv file at [view.qiime2](https://view.qiime2.org). The important features with regard to sample clusters are not a single arrow but by the log ratio between features represented by arrows pointing in different directions. A visualization tool for these log ratios is coming soon to QIIME. 
 
-![](etc/img6.png)
+![](etc/img8.png)
 
 From this visualization we noticed that BodySite seems to explain the clusters well. We can run [PERMANOVA](https://docs.qiime2.org/2019.1/plugins/available/diversity/beta-group-significance/) on the distances to get a statistical significance for this. 
 
@@ -131,7 +131,7 @@ From this visualization we noticed that BodySite seems to explain the clusters w
 
 Indeed we can now see that the clusters we saw in the biplot were significant by viewing the BodySite_significance.qzv at [view.qiime2](https://view.qiime2.org).
 
-![](etc/img7.png)
+![](etc/img9.png)
 
 ## Citation 
 

diff --git a/ipynb/tutorials/qiime2-moving-pictures-tutorial/BodySite_significance.qzv b/ipynb/tutorials/qiime2-moving-pictures-tutorial/BodySite_significance.qzv
diff --git a/ipynb/tutorials/qiime2-moving-pictures-tutorial/biplot.qzv b/ipynb/tutorials/qiime2-moving-pictures-tutorial/biplot.qzv
diff --git a/ipynb/tutorials/qiime2-moving-pictures-tutorial/distance.qza b/ipynb/tutorials/qiime2-moving-pictures-tutorial/distance.qza
diff --git a/ipynb/tutorials/qiime2-moving-pictures-tutorial/ordination.qza b/ipynb/tutorials/qiime2-moving-pictures-tutorial/ordination.qza