Psych 45: Semantic memory demo stats

In [37]:

    

%matplotlib inline
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import scipy as sp
sns.set(style='ticks', context='poster', font_scale=1)


    

In [38]:

    

data = pd.read_csv('/Users/Pam_sf_wang/Documents/Psych45/Psych45_semantic_demo_temp.csv',
                  index_col=[0],header=[0, 1], skipinitialspace=True)
data.head()


    

    
Out[38]:






  

    

      

      
fruit
      
sport
      
bird
      
vehicle
      
...
      
crime
      
vegetable
      
Unnamed: 19_level_0
      
Unnamed: 20_level_0
      
Unnamed: 21_level_0
      
Unnamed: 22_level_0
    
    

      
Timestamp
      
apple
      
fig
      
strawberry
      
football
      
hockey
      
wrestling
      
ostrich
      
wren
      
robin
      
boat
      
...
      
embezzling
      
murder
      
vagrancy
      
parsley
      
carrot
      
onion
      
Unnamed: 19_level_1
      
Unnamed: 20_level_1
      
Unnamed: 21_level_1
      
Unnamed: 22_level_1
    
  
  

    

      
4/26/16 11:47
      
1
      
4
      
2
      
1
      
1
      
5
      
5
      
2
      
1
      
3
      
...
      
4
      
2
      
6
      
6
      
2
      
3
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4/28/16 11:04
      
2
      
6
      
2
      
1
      
2
      
2
      
2
      
5
      
3
      
2
      
...
      
2
      
1
      
2
      
3
      
1
      
1
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4/28/16 11:05
      
1
      
3
      
1
      
1
      
1
      
2
      
2
      
1
      
1
      
2
      
...
      
2
      
1
      
5
      
1
      
1
      
2
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4/28/16 11:06
      
1
      
1
      
1
      
1
      
1
      
1
      
3
      
1
      
1
      
1
      
...
      
1
      
1
      
7
      
7
      
1
      
1
      
NaN
      
NaN
      
NaN
      
NaN
    
    

      
4/28/16 11:24
      
1
      
2
      
1
      
2
      
2
      
2
      
1
      
2
      
1
      
1
      
...
      
2
      
1
      
2
      
4
      
1
      
3
      
NaN
      
NaN
      
NaN
      
NaN
    
  

5 rows × 22 columns

In [39]:

    

print 'We currently have data from ' + str(data.count()[0]) + ' students.'


    

    




We currently have data from 340 students.

In [42]:

    

df = data.unstack().reset_index(name='rating')
df.rename(columns={'level_0': 'category', 'Timestamp': 'item', 'level_2': 'timestamp'}, inplace=True)
df = df[np.isfinite(df['rating'])]
df.head()


    

    
Out[42]:






  

    

      

      
category
      
item
      
timestamp
      
rating
    
  
  

    

      
0
      
fruit
      
apple
      
4/26/16 11:47
      
1
    
    

      
1
      
fruit
      
apple
      
4/28/16 11:04
      
2
    
    

      
2
      
fruit
      
apple
      
4/28/16 11:05
      
1
    
    

      
3
      
fruit
      
apple
      
4/28/16 11:06
      
1
    
    

      
4
      
fruit
      
apple
      
4/28/16 11:24
      
1
    
  

In [43]:

    

category_list = df.category.unique()
#category_list =(['fruit', 'sport', 'bird', 'vehicle', 'crime', 'vegetable'])
category_list


    

    
Out[43]:





array(['fruit', 'sport', 'bird', 'vehicle', 'crime', 'vegetable'], dtype=object)

In [44]:

    




    

    
Out[44]:





array(['fruit', 'sport', 'bird', 'vehicle', 'crime', 'vegetable'], dtype=object)






    

In [45]:

    

f, axes = plt.subplots(ncols=len(category_list), figsize=(15, 3), sharey=True)
plt.locator_params(nbins=5)
first = True

for ax, category in zip(axes, category_list):
    ax.hlines(y=1, xmin=-1, xmax=4, linestyles='dashed', colors='green')
    g = sns.pointplot(x='item', y='rating', ax=ax, jitter=True, alpha=.4, 
                      ci=95, palette=['darkgray'],
                      data=df.loc[df.category == category])
    g.set_title(category)
    g.set_ylabel('')
    g.set_xlabel('')
    g.set_xticklabels(df.loc[df.category == category].item.unique(), rotation=90)
    
f.text(0.07, 0.5, 'Rating', va='center', rotation='vertical', fontsize='xx-large')
sns.despine()


    

In [19]:

    

f, ax = plt.subplots(ncols=1, figsize=(10, 4), sharey=True)
g = sns.stripplot(x='item', y='rating', jitter=True, alpha=.1, size=12, linewidth=1,
                  data=df.loc[df.category == 'fruit'], 
                  order=['apple', 'strawberry', 'fig'],
                  palette=['limegreen', 'hotpink', 'mediumpurple'], ax=ax)
g.set_xlabel('')


    

    
Out[19]:





<matplotlib.text.Text at 0x110a1e250>






    

In [20]:

    

f, ax = plt.subplots(ncols=1, figsize=(10, 4), sharey=True)
g = sns.stripplot(x='item', y='rating', jitter=True, alpha=.1, size=12, linewidth=1,
                  data=df.loc[df.category == 'sport'], 
                  order=['football', 'hockey', 'wrestling'],
                  palette=['peru', 'black', 'blue'], ax=ax)
g.set_xlabel('')


    

    
Out[20]:





<matplotlib.text.Text at 0x110a4c950>






    

In [21]:

    

f, ax = plt.subplots(ncols=1, figsize=(10, 4), sharey=True)
g = sns.stripplot(x='item', y='rating', jitter=True, alpha=.1, size=12, linewidth=1,
                  data=df.loc[df.category == 'vehicle'], 
                  order=['car', 'boat', 'tricycle'],
                  palette=['gray', 'deepskyblue', 'crimson'], ax=ax)
g.set_xlabel('')


    

    
Out[21]:





<matplotlib.text.Text at 0x110a07850>






    

In [ ]: