Merge pull request #172 from ironmussa/develop

Changes for 1.2.1

Dockerfile

@@ -6,7 +6,7 @@ MAINTAINER Jupyter Project <[email protected]>
 
 USER root
 
-RUN pip install --no-cache-dir optimuspyspark
+RUN pip install --no-cache-dir optimuspyspark -U
 RUN git clone https://github.com/ironmussa/Optimus-examples.git /home/jovyan/work
 RUN chmod -R 777 /home/jovyan/work
 

docs/source/sections/analyzing.rst

@@ -387,7 +387,7 @@ Lets say we want to plot a histogram of frecuencies for the ``product`` column.
 
 .. code:: python
 
-  productDf = analyzer.get_data_frame.select("product") #or df.select("product")
+  productDf = analyzer.df.select("product") #or df.select("product")
   hist_dictPro = analyzer.get_categorical_hist(df_one_col=productDf, num_bars=10)
   print(hist_dictPro)
 
@@ -417,7 +417,7 @@ Lets say we want to plot a histogram of frequencies for the ``price`` column. We
 
 .. code:: python
 
-  priceDf = analyzer.get_data_frame.select("price") #or df.select("price")
+  priceDf = analyzer.df.select("price") #or df.select("price")
   hist_dictPri = analyzer.get_numerical_hist(df_one_col=priceDf, num_bars=10)
   print(hist_dictPri)
 

docs/source/sections/feature.rst

@@ -303,7 +303,7 @@ Let's create a sample dataframe to see what vector assembler does:
 
     # Show assembled df
     print("Assembled columns 'hour', 'mobile', 'userFeatures' to vector column 'features'")
-    transform.get_data_frame.select("features", "clicked").show(truncate=False)
+    transform.df.select("features", "clicked").show(truncate=False)
 
 
 +-----------------------+-------+