diff --git a/src/templates/Exploratory_Charts-Movie_Data-Latest.html b/src/templates/Exploratory_Charts-Movie_Data-Latest.html index 70677dd..0f76e19 100644 --- a/src/templates/Exploratory_Charts-Movie_Data-Latest.html +++ b/src/templates/Exploratory_Charts-Movie_Data-Latest.html @@ -1,7 +1,7 @@
-
In [1]:
+
In [3]:
import numpy as np # linear algebra
@@ -15,7 +15,7 @@
-
In [2]:
+
In [4]:
from subprocess import check_output
@@ -48,7 +48,7 @@
-
In [3]:
+
In [8]:
import os
@@ -67,6 +67,7 @@
 from sklearn import neighbors
 from sklearn import linear_model
 from pandas.core import datetools
+from pandas.core import datetools
 %matplotlib inline
@@ -74,29 +75,10 @@
-
-
- - -
- -
- - -
-
C:\Users\alurus\AppData\Local\Continuum\Anaconda3\lib\site-packages\statsmodels\compat\pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.
-  from pandas.core import datetools
-
-
-
- -
-
-
-
In [20]:
+
In [5]:
f = pd.read_csv("C:/Users/alurus/GIT-Repository/VIZ Day/pyDataVizDay2/data/raw/movie_metadata.csv")
@@ -109,7 +91,7 @@
-
In [21]:
+
In [7]:
data=DataFrame(f)
@@ -126,7 +108,7 @@
 
 

 
-
Out[21]:

+
Out[7]:

 
 
 
@@ -235,7 +217,7 @@
 

 

 

-
In [22]:

+
In [9]:

 

     

 
X_data=data.dtypes[data.dtypes!='object'].index
@@ -253,7 +235,7 @@
 
 

 
-
Out[22]:

+
Out[9]:

 
 
 
@@ -343,16 +325,24 @@
 

 

 
+

+

+

+

+

+
GETTING Correllation matrix

+

+

 

 

 

-
In [32]:

+
In [10]:

 

     

 
# GETTING Correllation matrix
 corr_mat=X_train.corr(method='pearson')
 plt.figure(figsize=(20,10))
-sns.heatmap(corr_mat,vmax=1,square=True,annot=True,cmap='cubehelix')
+sns.heatmap(corr_mat,vmax=1,square=True,annot=True,cmap='Oranges');
 

 
 

@@ -363,19 +353,6 @@
 

 
 
-

-
-
Out[32]:

-
-
-
-
-

-
<matplotlib.axes._subplots.AxesSubplot at 0x106d77f0>

-

-
-

-
 

 
 

@@ -385,2470 +362,2439 @@
 
 

 
 

@@ -2861,39 +2807,7 @@ uhbmo2gAAAAASUVORK5CYII=
 

 

 

-
In [19]:

-

-    

-
!jupyter nbconvert Exploratory_Charts-Movie_Data-Copy2.ipynb --template basic
-

-
-

-

-

-
-

-

-
-
-

-
-

-
-
-

-
[NbConvertApp] Converting notebook Exploratory_Charts-Movie_Data-Copy2.ipynb to html
-[NbConvertApp] Writing 206376 bytes to Exploratory_Charts-Movie_Data-Copy2.html
-

-

-

-
-

-

-
-

-

-

-
In [5]:

+
In [11]:

 

     

 
df = pd.read_csv('C:/Users/alurus/GIT-Repository/VIZ Day/pyDataVizDay2/data/raw/movie_metadata.csv')
@@ -2906,7 +2820,7 @@ uhbmo2gAAAAASUVORK5CYII=
 

 

 

-
In [6]:

+
In [12]:

 

     

 
df.head()
@@ -2922,7 +2836,7 @@ uhbmo2gAAAAASUVORK5CYII=
 
 

 
-
Out[6]:

+
Out[12]:

 
 
 
@@ -3100,10 +3014,18 @@ uhbmo2gAAAAASUVORK5CYII=
 

 

 
+

+

+

+

+

+
Director Vs Share by Year

+

+

 

 

 

-
In [7]:

+
In [13]:

 

     

 
df['diff_gross'] = df['gross'] - df['budget']
@@ -3118,9 +3040,9 @@ uhbmo2gAAAAASUVORK5CYII=
 
 
 fig,ax = plt.subplots(figsize=(8,6))
-sns.heatmap(director_budge_pivot['diff_gross'],vmin=0,annot=False,linewidth=.5,ax=ax,cmap='PuBu')
-plt.title('Director vs Year and diff_gross')
-plt.ylabel('Year')
+sns.heatmap(director_budge_pivot['diff_gross'],vmin=0,annot=False,linewidth=.5,ax=ax,cmap='Oranges')
+plt.title('Director vs Year and Share')
+plt.ylabel('Year');
 

 
 

@@ -3131,19 +3053,6 @@ uhbmo2gAAAAASUVORK5CYII=
 

 
 
-

-
-
Out[7]:

-
-
-
-
-

-
<matplotlib.text.Text at 0xd419a58>

-

-
-

-
 

 
 

@@ -3153,582 +3062,570 @@ uhbmo2gAAAAASUVORK5CYII=
 
 

 
 

@@ -3741,7 +3638,7 @@ OJQeAAAAAElFTkSuQmCC
 

 

 

-
In [8]:

+
In [14]:

 

     

 
data = pd.read_csv("C:/Users/alurus/GIT-Repository/VIZ Day/pyDataVizDay2/data/raw/movie_metadata.csv")
@@ -3751,15 +3648,23 @@ OJQeAAAAAElFTkSuQmCC
 

 

 
+

+

+

+

+

+
IMDB Score In Histogram

+

+

 

 

 

-
In [40]:

+
In [32]:

 

     

-
matplotlib.rcParams['figure.figsize'] = (9.0, 5.0)
+
matplotlib.rcParams['figure.figsize'] = (18, 9.0)
 scores = pd.DataFrame({"imdb score":data["imdb_score"]})
-scores.hist(bins=20)
+scores.hist(bins=20);
 

 
 

@@ -3770,19 +3675,6 @@ OJQeAAAAAElFTkSuQmCC
 

 
 
-

-
-
Out[40]:

-
-
-
-
-

-
array([[<matplotlib.axes._subplots.AxesSubplot object at 0x0000000012C971D0>]], dtype=object)

-

-
-

-
 

 
 

@@ -3791,140 +3683,183 @@ OJQeAAAAAElFTkSuQmCC
 
 
 

-
 

@@ -3934,10 +3869,18 @@ TkSuQmCC
 

 

 
+

+

+

+

+

+
IMDB Score By Count Plot

+

+

 

 

 

-
In [9]:

+
In [26]:

 

     

 
plt.figure(figsize = (18, 9))
@@ -4191,13 +4134,21 @@ n0ty44m7n1Br/WKLfgCA5fNRDgAAAKAZH+UAAAAAmhFMAAAAAM0IJgAAAIBmBBMAAABAM/8fUHwp
 

 

 
+

+

+

+

+

+
Count by Content Rating - Count Plot

+

+

 

 

 

-
In [10]:

+
In [21]:

 

     

-
plt.figure(figsize = (12, 9))
+
plt.figure(figsize = (11, 4))
 sns.countplot(x = 'content_rating', data = data)
 xt = plt.xticks(rotation=56)
 

@@ -4218,293 +4169,257 @@ n0ty44m7n1Br/WKLfgCA5fNRDgAAAKAZH+UAAAAAmhFMAAAAAM0IJgAAAIBmBBMAAABAM/8fUHwp
 
 
 

-
-

-
In [ ]:

+

+

 

-    

-
 
-

-
+

+
Content Rating Vs IBDB Score - Box Plot

 

 

-

-
 

 

 

@@ -4886,14 +4796,23 @@ RKRo/x9J7Ry013cL/gAAAABJRU5ErkJggg==
 

 

 
+

+

+

+

+

+
Content Rating Vs IBDB Score - Violin Plot

+

+

 

 

 

-
In [14]:

+
In [33]:

 

     

 
plt.figure(figsize = (11, 4))
 sns.violinplot('content_rating', 'imdb_score', data = data)
+xt = plt.xticks(rotation=45)
 

 
 

@@ -4904,19 +4823,6 @@ RKRo/x9J7Ry013cL/gAAAABJRU5ErkJggg==
 

 
 
-

-
-
Out[14]:

-
-
-
-
-

-
<matplotlib.axes._subplots.AxesSubplot at 0xd1f2828>

-

-
-

-
 

 
 

@@ -4925,687 +4831,767 @@ RKRo/x9J7Ry013cL/gAAAABJRU5ErkJggg==
 
 
 

-
 

@@ -5615,6 +5601,51 @@ KjQVRVEURVGUQPj/AQny1vTwN90tAAAAAElFTkSuQmCC
 

 

 
+

+

+

+
In [39]:

+

+    

+
!jupyter nbconvert Exploratory_Charts-Movie_Data-Latest_a.ipynb --template basic
+

+
+

+

+

+
+

+

+
+
+

+
+

+
+
+

+
[NbConvertApp] Converting notebook Exploratory_Charts-Movie_Data-Latest_a.ipynb to html
+[NbConvertApp] Writing 397209 bytes to Exploratory_Charts-Movie_Data-Latest_a.html
+

+

+

+
+

+

+
+

+

+

+
In [ ]:

+

+    

+
 
+

+
+

+

+

+