waylon/pyDataVizDay
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
pyDataVizDay/notebooks/Explore Movie Dataset.html

721 lines
23 KiB
HTML
Raw Blame History

<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="Explore-Movie-Dataset">Explore Movie Dataset<a class="anchor-link" href="#Explore-Movie-Dataset">&#182;</a></h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[1]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">import</span> <span class="nn">settings</span>
<span class="kn">import</span> <span class="nn">etl</span>
<span class="o">%</span><span class="k">matplotlib</span> inline
<span class="o">%</span><span class="k">load_ext</span> watermark
<span class="o">%</span><span class="k">watermark</span> -d -t -v -m -p pea,pandas
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="prompt"></div>
<div class="output_subarea output_stream output_stdout output_text">
<pre>2017-06-26 18:57:49
CPython 3.6.1
IPython 6.1.0
pea 0.0.7
pandas 0.20.2
compiler : MSC v.1900 64 bit (AMD64)
system : Windows
release : 7
machine : AMD64
processor : Intel64 Family 6 Model 42 Stepping 7, GenuineIntel
CPU cores : 8
interpreter: 64bit
</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[2]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">data</span> <span class="o">=</span> <span class="n">etl</span><span class="o">.</span><span class="n">Data</span><span class="p">()</span>
<span class="n">data</span><span class="o">.</span><span class="n">load</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="Available-Columns">Available Columns<a class="anchor-link" href="#Available-Columns">&#182;</a></h2>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[3]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">data</span><span class="o">.</span><span class="n">movie</span><span class="o">.</span><span class="n">columns</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="prompt output_prompt">Out[3]:</div>
<div class="output_text output_subarea output_execute_result">
<pre>Index([&#39;color&#39;, &#39;director_name&#39;, &#39;num_critic_for_reviews&#39;, &#39;duration&#39;,
&#39;director_facebook_likes&#39;, &#39;actor_3_facebook_likes&#39;, &#39;actor_2_name&#39;,
&#39;actor_1_facebook_likes&#39;, &#39;gross&#39;, &#39;genres&#39;, &#39;actor_1_name&#39;,
&#39;movie_title&#39;, &#39;num_voted_users&#39;, &#39;cast_total_facebook_likes&#39;,
&#39;actor_3_name&#39;, &#39;facenumber_in_poster&#39;, &#39;plot_keywords&#39;,
&#39;movie_imdb_link&#39;, &#39;num_user_for_reviews&#39;, &#39;language&#39;, &#39;country&#39;,
&#39;content_rating&#39;, &#39;budget&#39;, &#39;title_year&#39;, &#39;actor_2_facebook_likes&#39;,
&#39;imdb_score&#39;, &#39;aspect_ratio&#39;, &#39;movie_facebook_likes&#39;],
dtype=&#39;object&#39;)</pre>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="plotting-with-IPlotter">plotting with IPlotter<a class="anchor-link" href="#plotting-with-IPlotter">&#182;</a></h2><p>This example is using my own branch of IPlotter which builds the dictionary from a pandas DataFrame. Much less verbose, but can be done with the current version on PyPI.</p>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[5]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">from</span> <span class="nn">iplotter</span> <span class="k">import</span> <span class="n">C3Plotter</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[6]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">c3</span> <span class="o">=</span> <span class="n">C3Plotter</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h3 id="Timeseries-of-mean-gross">Timeseries of mean gross<a class="anchor-link" href="#Timeseries-of-mean-gross">&#182;</a></h3>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[46]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">plot_data</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">movie</span><span class="o">.</span><span class="n">groupby</span><span class="p">([</span><span class="s1">&#39;title_year&#39;</span><span class="p">])</span><span class="o">.</span><span class="n">mean</span><span class="p">()[[</span><span class="s1">&#39;gross&#39;</span><span class="p">]]</span><span class="o">.</span><span class="n">fillna</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="n">c3</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">plot_data</span><span class="p">,</span> <span class="n">zoom</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="prompt output_prompt">Out[46]:</div>
<div class="output_html rendered_html output_subarea output_execute_result">
<iframe srcdoc="
<!-- Load c3.css -->
<link href='https://cdnjs.cloudflare.com/ajax/libs/c3/0.4.10/c3.min.css' rel='stylesheet' type='text/css'/>
<!-- Load d3.js and c3.js -->
<script src='http://d3js.org/d3.v3.min.js' charset='utf-8'></script>
<script src='http://cdnjs.cloudflare.com/ajax/libs/c3/0.4.10/c3.min.js'></script>
<h1></h1>
<div id=chart style='width: 100%; height: 100%'></div>
<script>
var chart = document.getElementById('chart');
var data = {
'size': {
'height': 300
},
'data': {
'x': 'x',
'type': 'line',
'axes': {
'gross': 'y',
'x': 'y'
},
'columns': [
[
'gross',
0.0,
3000000.0,
0.0,
26435.0,
1408975.0,
0.0,
0.0,
2300000.0,
0.0,
3000000.0,
163245.0,
184925485.0,
0.0,
110428945.0,
80350000.0,
0.0,
102797150.0,
0.0,
0.0,
0.0,
22025000.0,
7927.0,
2956000.0,
0.0,
8000000.0,
0.0,
36000000.0,
20500000.0,
4934530.5,
0.0,
0.0,
27200000.0,
0.0,
25000000.0,
32000000.0,
43650000.0,
11033517.5,
42950000.0,
38237907.166666664,
69310231.8,
6100000.0,
43100000.0,
36757685.5,
41711931.0,
10450000.0,
27247057.75,
67501217.5,
102919529.0,
55052942.85714286,
124409732.33333333,
71117623.5,
106290809.28571428,
71542234.6,
63579571.428571425,
57697266.733333334,
41460781.52941176,
75037552.1875,
70192386.35714285,
62939598.73913044,
59223134.13333333,
44436464.04,
40233264.77419355,
41190351.833333336,
49678453.15151515,
78203971.25,
53844501.666666664,
63665195.14705882,
45302091.41304348,
59395666.16981132,
44909519.98550725,
42044174.25263158,
44793772.43103448,
38377007.96124031,
38072176.27710843,
42172627.58083832,
43255716.92553192,
43511151.485,
48727746.72327044,
40726529.11,
41159143.29064039,
39237855.9537037,
46267501.02234637,
44573509.378109455,
46207440.2,
49908326.01005025,
45785836.64397906,
62873527.67955801,
56158357.77540107,
62412136.94610778,
66530966.47552448,
76924035.8918919
],
[
'x',
'1916.0',
'1920.0',
'1925.0',
'1927.0',
'1929.0',
'1930.0',
'1932.0',
'1933.0',
'1934.0',
'1935.0',
'1936.0',
'1937.0',
'1938.0',
'1939.0',
'1940.0',
'1941.0',
'1942.0',
'1943.0',
'1944.0',
'1945.0',
'1946.0',
'1947.0',
'1948.0',
'1949.0',
'1950.0',
'1951.0',
'1952.0',
'1953.0',
'1954.0',
'1955.0',
'1956.0',
'1957.0',
'1958.0',
'1959.0',
'1960.0',
'1961.0',
'1962.0',
'1963.0',
'1964.0',
'1965.0',
'1966.0',
'1967.0',
'1968.0',
'1969.0',
'1970.0',
'1971.0',
'1972.0',
'1973.0',
'1974.0',
'1975.0',
'1976.0',
'1977.0',
'1978.0',
'1979.0',
'1980.0',
'1981.0',
'1982.0',
'1983.0',
'1984.0',
'1985.0',
'1986.0',
'1987.0',
'1988.0',
'1989.0',
'1990.0',
'1991.0',
'1992.0',
'1993.0',
'1994.0',
'1995.0',
'1996.0',
'1997.0',
'1998.0',
'1999.0',
'2000.0',
'2001.0',
'2002.0',
'2003.0',
'2004.0',
'2005.0',
'2006.0',
'2007.0',
'2008.0',
'2009.0',
'2010.0',
'2011.0',
'2012.0',
'2013.0',
'2014.0',
'2015.0',
'2016.0'
]
]
},
'subchart': {
'show': false
},
'point': {
'show': false
},
'grid': {
'x': {
'show': false
},
'y': {
'show': false
}
},
'axis': {
'x': {},
'y': {},
'y2': {}
},
'zoom': {
'enabled': true
}
};
data['bindto']='#chart'
c3.generate(data);
</script>
" src="" width="800" height="420" frameborder="0" sandbox="allow-scripts"></iframe>
</div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[25]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">country_group</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">movie</span><span class="o">.</span><span class="n">groupby</span><span class="p">(</span><span class="s1">&#39;country&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">()[</span><span class="s1">&#39;duration&#39;</span><span class="p">]</span>
<span class="n">counts</span> <span class="o">=</span> <span class="n">country_group</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span>
<span class="n">countries</span> <span class="o">=</span> <span class="n">country_group</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">values</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[47]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="kn">from</span> <span class="nn">iplotter</span> <span class="k">import</span> <span class="n">PlotlyPlotter</span>
<span class="kn">from</span> <span class="nn">IPython.display</span> <span class="k">import</span> <span class="n">HTML</span>
<span class="n">plotly</span> <span class="o">=</span> <span class="n">PlotlyPlotter</span><span class="p">()</span>
<span class="n">c3_plotter</span> <span class="o">=</span> <span class="n">C3Plotter</span><span class="p">()</span>
<span class="n">plotly_chart</span> <span class="o">=</span> <span class="p">[{</span>
<span class="s2">&quot;type&quot;</span><span class="p">:</span> <span class="s1">&#39;choropleth&#39;</span><span class="p">,</span>
<span class="s2">&quot;locationmode&quot;</span><span class="p">:</span> <span class="s1">&#39;country names&#39;</span><span class="p">,</span>
<span class="s2">&quot;locations&quot;</span><span class="p">:</span> <span class="n">countries</span><span class="p">,</span>
<span class="s2">&quot;z&quot;</span><span class="p">:</span> <span class="n">counts</span><span class="p">,</span>
<span class="s2">&quot;zmin&quot;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
<span class="s2">&quot;zmax&quot;</span><span class="p">:</span> <span class="nb">max</span><span class="p">(</span><span class="n">counts</span><span class="p">),</span>
<span class="s2">&quot;colorscale&quot;</span><span class="p">:</span> <span class="p">[</span>
<span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="s1">&#39;rgb(242,240,247)&#39;</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.2</span><span class="p">,</span> <span class="s1">&#39;rgb(218,218,235)&#39;</span><span class="p">],</span>
<span class="p">[</span><span class="mf">0.4</span><span class="p">,</span> <span class="s1">&#39;rgb(188,189,220)&#39;</span><span class="p">],</span> <span class="p">[</span><span class="mf">0.6</span><span class="p">,</span> <span class="s1">&#39;rgb(158,154,200)&#39;</span><span class="p">],</span>
<span class="p">[</span><span class="mf">0.8</span><span class="p">,</span> <span class="s1">&#39;rgb(117,107,177)&#39;</span><span class="p">],</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="s1">&#39;rgb(84,39,143)&#39;</span><span class="p">]</span>
<span class="p">],</span>
<span class="s2">&quot;colorbar&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;title&quot;</span><span class="p">:</span> <span class="s1">&#39;Count&#39;</span><span class="p">,</span>
<span class="s2">&quot;thickness&quot;</span><span class="p">:</span> <span class="mi">10</span>
<span class="p">},</span>
<span class="s2">&quot;marker&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;line&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;color&quot;</span><span class="p">:</span> <span class="s1">&#39;rgb(255,255,255)&#39;</span><span class="p">,</span>
<span class="s2">&quot;width&quot;</span><span class="p">:</span> <span class="mi">2</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="p">}]</span>
<span class="n">plotly_layout</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;title&quot;</span><span class="p">:</span> <span class="s1">&#39;Movie Counts by Country&#39;</span><span class="p">,</span>
<span class="s2">&quot;geo&quot;</span><span class="p">:</span> <span class="p">{</span>
<span class="s2">&quot;scope&quot;</span><span class="p">:</span> <span class="s1">&#39;country names&#39;</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">}</span>
<span class="n">country_plot</span> <span class="o">=</span> <span class="n">plotly</span><span class="o">.</span><span class="n">plot</span><span class="p">(</span><span class="n">data</span><span class="o">=</span><span class="n">plotly_chart</span><span class="p">)</span>
</pre></div>
</div>
</div>
</div>
</div>
<div class="cell border-box-sizing text_cell rendered"><div class="prompt input_prompt">
</div>
<div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h3 id="Movies-by-Country">Movies by Country<a class="anchor-link" href="#Movies-by-Country">&#182;</a></h3><iframe srcdoc="
<!-- Load d3.js and plotly.js -->
<script src='https://cdnjs.cloudflare.com/ajax/libs/d3/3.5.6/d3.min.js'></script>
<script src='https://code.jquery.com/jquery-2.1.4.min.js'></script>
<script src='https://cdn.plot.ly/plotly-latest.min.js'></script>
<div id=chart style='width: 100%; height: 100%' ></div>
<script>
var chart = document.getElementById('chart');
Plotly.plot(chart, [
{
'type': 'choropleth',
'locationmode': 'country names',
'locations': [
'Afghanistan',
'Argentina',
'Aruba',
'Australia',
'Bahamas',
'Belgium',
'Brazil',
'Bulgaria',
'Cambodia',
'Cameroon',
'Canada',
'Chile',
'China',
'Colombia',
'Czech Republic',
'Denmark',
'Dominican Republic',
'Egypt',
'Finland',
'France',
'Georgia',
'Germany',
'Greece',
'Hong Kong',
'Hungary',
'Iceland',
'India',
'Indonesia',
'Iran',
'Ireland',
'Israel',
'Italy',
'Japan',
'Kenya',
'Kyrgyzstan',
'Libya',
'Mexico',
'Netherlands',
'New Line',
'New Zealand',
'Nigeria',
'Norway',
'Official site',
'Pakistan',
'Panama',
'Peru',
'Philippines',
'Poland',
'Romania',
'Russia',
'Slovakia',
'Slovenia',
'South Africa',
'South Korea',
'Soviet Union',
'Spain',
'Sweden',
'Switzerland',
'Taiwan',
'Thailand',
'Turkey',
'UK',
'USA',
'United Arab Emirates',
'West Germany'
],
'z': [
1,
4,
1,
54,
1,
4,
8,
1,
1,
1,
126,
1,
30,
1,
3,
11,
1,
1,
1,
154,
1,
97,
2,
17,
2,
3,
31,
1,
4,
12,
4,
23,
23,
1,
1,
1,
17,
5,
1,
15,
1,
8,
1,
0,
1,
1,
1,
5,
4,
11,
1,
1,
8,
14,
1,
33,
6,
3,
2,
5,
1,
445,
3801,
1,
3
],
'zmin': 0,
'zmax': 3801,
'colorscale': [
[
0,
'rgb(242,240,247)'
],
[
0.2,
'rgb(218,218,235)'
],
[
0.4,
'rgb(188,189,220)'
],
[
0.6,
'rgb(158,154,200)'
],
[
0.8,
'rgb(117,107,177)'
],
[
1,
'rgb(84,39,143)'
]
],
'colorbar': {
'title': 'Count',
'thickness': 10
},
'marker': {
'line': {
'color': 'rgb(255,255,255)',
'width': 2
}
}
}
], null);
</script>
" src="" width="800" height="420" frameborder="0" sandbox="allow-scripts"></iframe>
</div>
</div>
</div>
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="prompt input_prompt">In&nbsp;[&nbsp;]:</div>
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span>
</pre></div>
</div>
</div>
</div>
</div>
Reference in a new issue View git blame Copy permalink