{"id":1032,"date":"2021-11-07T01:35:48","date_gmt":"2021-11-07T08:35:48","guid":{"rendered":"https:\/\/gantovnik.com\/bio-tips\/?p=1032"},"modified":"2021-11-07T01:46:08","modified_gmt":"2021-11-07T09:46:08","slug":"184-creating-a-boxplot-using-seaborn","status":"publish","type":"post","link":"https:\/\/gantovnik.com\/bio-tips\/2021\/11\/184-creating-a-boxplot-using-seaborn\/","title":{"rendered":"#183 Creating a boxplot using seaborn"},"content":{"rendered":"<pre class=\"brush: python; title: ; notranslate\" title=\"\">\r\nimport numpy as np\r\nimport pandas as pd\r\nimport seaborn as sns\r\nimport matplotlib.pyplot as plt\r\nimport os\r\nos.chdir(r'D:\\projects\\wordpress\\ex184') \r\nos.getcwd()\r\nurl = &quot;https:\/\/archive.ics.uci.edu\/ml\/machine-learning-databases\/auto-mpg\/auto-mpg.data&quot;\r\ndf = pd.read_csv(url)\r\ncolumn_names = &#x5B;'mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'year', 'origin', 'name']\r\ndf = pd.read_csv(url, names= column_names, delim_whitespace=True)\r\nprint(df.head())\r\n#Convert the horsepower and year data types to float and integer\r\ndf.loc&#x5B;df.horsepower == '?', 'horsepower'] = np.nan\r\ndf&#x5B;'horsepower'] = pd.to_numeric(df&#x5B;'horsepower'])\r\ndf&#x5B;'full_date'] = pd.to_datetime(df.year, format='%y')\r\ndf&#x5B;'year'] = df&#x5B;'full_date'].dt.year\r\n#Plot the average horsepower per year\r\nsns.boxplot(data=df, x=&quot;cylinders&quot;, y=&quot;horsepower&quot;)\r\nplt.savefig('ex184.jpg', dpi=300)\r\n<\/pre>\n<p><img data-recalc-dims=\"1\" decoding=\"async\" src=\"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex184.jpg?resize=1080%2C720&#038;ssl=1\" alt=\"\" width=\"1080\" height=\"720\" class=\"alignnone size-full wp-image-1033\" srcset=\"https:\/\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex184.jpg 1800w, https:\/\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex184-1280x853.jpg 1280w, https:\/\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex184-980x653.jpg 980w, https:\/\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex184-480x320.jpg 480w\" sizes=\"(min-width: 0px) and (max-width: 480px) 480px, (min-width: 481px) and (max-width: 980px) 980px, (min-width: 981px) and (max-width: 1280px) 1280px, (min-width: 1281px) 1800px, 100vw\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import os os.chdir(r&#8217;D:\\projects\\wordpress\\ex184&#8242;) os.getcwd() url = &quot;https:\/\/archive.ics.uci.edu\/ml\/machine-learning-databases\/auto-mpg\/auto-mpg.data&quot; df = pd.read_csv(url) column_names = &#x5B;&#8217;mpg&#8217;, &#8216;cylinders&#8217;, &#8216;displacement&#8217;, &#8216;horsepower&#8217;, &#8216;weight&#8217;, &#8216;acceleration&#8217;, &#8216;year&#8217;, &#8216;origin&#8217;, &#8216;name&#8217;] df = pd.read_csv(url, names= column_names, delim_whitespace=True) print(df.head()) #Convert the horsepower and year data types to float and integer [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"nf_dc_page":"","_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","_lmt_disableupdate":"yes","_lmt_disable":"","jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[2],"tags":[],"class_list":["post-1032","post","type-post","status-publish","format-standard","hentry","category-python"],"modified_by":"gantovnik","jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p8bH0k-gE","jetpack_likes_enabled":true,"jetpack-related-posts":[{"id":1037,"url":"https:\/\/gantovnik.com\/bio-tips\/2021\/11\/185-creating-a-scatter-plot-using-seaborn\/","url_meta":{"origin":1032,"position":0},"title":"#185 Creating a scatter plot using seaborn","author":"gantovnik","date":"2021-11-07","format":false,"excerpt":"[code language=\"python\"] import matplotlib.pyplot as plt import numpy as np import pandas as pd import os import seaborn as sns os.chdir(r'D:\\projects\\wordpress\\ex185') os.getcwd() url = \"https:\/\/archive.ics.uci.edu\/ml\/machine-learning-databases\/auto-mpg\/auto-mpg.data\" df = pd.read_csv(url) column_names = ['mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'year', 'origin', 'name'] df = pd.read_csv(url, names= column_names, delim_whitespace=True) df.loc[df.horsepower == '?', 'horsepower'] =\u2026","rel":"","context":"In &quot;python&quot;","block_context":{"text":"python","link":"https:\/\/gantovnik.com\/bio-tips\/category\/python\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex185b.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":1028,"url":"https:\/\/gantovnik.com\/bio-tips\/2021\/11\/183-creating-a-histogram-using-seaborn\/","url_meta":{"origin":1032,"position":1},"title":"#184 Creating a histogram using seaborn","author":"gantovnik","date":"2021-11-07","format":false,"excerpt":"[code language=\"python\"] import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import os os.chdir(r'D:\\projects\\wordpress\\ex183') os.getcwd() url = \"https:\/\/archive.ics.uci.edu\/ml\/machine-learning-databases\/auto-mpg\/auto-mpg.data\" df = pd.read_csv(url) column_names = ['mpg', 'cylinders', 'displacement', 'horsepower', 'weight', 'acceleration', 'year', 'origin', 'name'] df = pd.read_csv(url, names= column_names, delim_whitespace=True) print(df.head()) #Convert the horsepower and\u2026","rel":"","context":"In &quot;python&quot;","block_context":{"text":"python","link":"https:\/\/gantovnik.com\/bio-tips\/category\/python\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=1050%2C600&ssl=1 3x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex183.jpg?resize=1400%2C800&ssl=1 4x"},"classes":[]},{"id":1041,"url":"https:\/\/gantovnik.com\/bio-tips\/2021\/11\/186-generate-the-feature-importance\/","url_meta":{"origin":1032,"position":2},"title":"#186 Generate the feature importance","author":"gantovnik","date":"2021-11-07","format":false,"excerpt":"[code language=\"python\"] import pandas as pd import seaborn as sns import os import matplotlib.pyplot as plt os.chdir(r'D:\\projects\\wordpress\\ex186') sns.set(style=\"ticks\") # read the downloaded input data (marketing data) df = pd.read_csv('https:\/\/raw.githubusercontent.com\/TrainingByPackt\/Big-Data-Analysis-with-Python\/master\/Lesson07\/Dataset\/bank.csv', sep=';') df['y'].replace(['yes','no'],[1,0],inplace=True) df['default'].replace(['yes','no'],[1,0],inplace=True) df['housing'].replace(['yes','no'],[1,0],inplace=True) df['loan'].replace(['yes','no'],[1,0],inplace=True) corr_df = df.corr() sns.heatmap(corr_df, xticklabels=corr_df.columns.values, yticklabels=corr_df.columns.values, annot = True, annot_kws={'size':12}) heat_map=plt.gcf(); heat_map.set_size_inches(10,5) plt.xticks(fontsize=10); plt.yticks(fontsize=10); plt.savefig('ex186a.jpg', dpi=300)\u2026","rel":"","context":"In &quot;python&quot;","block_context":{"text":"python","link":"https:\/\/gantovnik.com\/bio-tips\/category\/python\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex186b.jpg?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex186b.jpg?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex186b.jpg?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex186b.jpg?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2021\/11\/ex186b.jpg?resize=1050%2C600&ssl=1 3x"},"classes":[]},{"id":1977,"url":"https:\/\/gantovnik.com\/bio-tips\/2023\/11\/396-seaborn-pairplot-example-with-lowess-regression\/","url_meta":{"origin":1032,"position":3},"title":"#396 Seaborn pairplot example with lowess regression","author":"gantovnik","date":"2023-11-16","format":false,"excerpt":"[code language=\"python\"] import matplotlib.pyplot as plt import seaborn as sns def plot_extra(x, y, **kwargs): if kwargs['label'] == first_label: sns.regplot(data=kwargs['data'], x=x.name, y=y.name, lowess=True, scatter=False, color=kwargs['color']) df = sns.load_dataset('iris') first_label = df['species'][0] pg = sns.pairplot(df, hue='species', plot_kws={'alpha': 0.8}, palette='rainbow') pg.map_offdiag(plot_extra, color='crimson', data=df) legend_dict = {h.get_label(): h for h in pg.legend.legend_handles} # the\u2026","rel":"","context":"In &quot;python&quot;","block_context":{"text":"python","link":"https:\/\/gantovnik.com\/bio-tips\/category\/python\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/11\/ex396.png?fit=1200%2C930&ssl=1&resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/11\/ex396.png?fit=1200%2C930&ssl=1&resize=350%2C200 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/11\/ex396.png?fit=1200%2C930&ssl=1&resize=525%2C300 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/11\/ex396.png?fit=1200%2C930&ssl=1&resize=700%2C400 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/11\/ex396.png?fit=1200%2C930&ssl=1&resize=1050%2C600 3x"},"classes":[]},{"id":1943,"url":"https:\/\/gantovnik.com\/bio-tips\/2023\/08\/385-scatterplot-matrix-using-seaborn-library\/","url_meta":{"origin":1032,"position":4},"title":"#385 Scatterplot matrix using seaborn library","author":"gantovnik","date":"2023-08-13","format":false,"excerpt":"[code language=\"python\"] #Scatterplot matrix using seaborn library import matplotlib.pyplot as plt #conda install -c anaconda seaborn import seaborn as sns sns.set_theme(style=\"ticks\") def main(): df = sns.load_dataset(\"penguins\") sns.pairplot(df, hue=\"species\") plt.savefig(\"ex385.png\", dpi=100) plt.show() if __name__ == '__main__': main() [\/code]","rel":"","context":"In &quot;plot&quot;","block_context":{"text":"plot","link":"https:\/\/gantovnik.com\/bio-tips\/category\/plot\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/08\/ex385.png?resize=350%2C200&ssl=1","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/08\/ex385.png?resize=350%2C200&ssl=1 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/08\/ex385.png?resize=525%2C300&ssl=1 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/08\/ex385.png?resize=700%2C400&ssl=1 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2023\/08\/ex385.png?resize=1050%2C600&ssl=1 3x"},"classes":[]},{"id":654,"url":"https:\/\/gantovnik.com\/bio-tips\/2020\/09\/107-tsa-data-2020-vs-2019\/","url_meta":{"origin":1032,"position":5},"title":"#107: TSA Data 2020 vs 2019","author":"gantovnik","date":"2020-09-28","format":false,"excerpt":"#107: TSA Data 2020 vs 2019 The TSA has started to publish the daily volume of passengers going through checkpoints on its website. The data set also includes the numbers from 2019 in order to measure the impact of travel as a result of COVID-19. https:\/\/www.tsa.gov\/coronavirus\/passenger-throughput [code language=\"python\"] from bs4\u2026","rel":"","context":"In &quot;python&quot;","block_context":{"text":"python","link":"https:\/\/gantovnik.com\/bio-tips\/category\/python\/"},"img":{"alt_text":"","src":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=350%2C200","width":350,"height":200,"srcset":"https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=350%2C200 1x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=525%2C300 1.5x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=700%2C400 2x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=1050%2C600 3x, https:\/\/i0.wp.com\/gantovnik.com\/bio-tips\/wp-content\/uploads\/2020\/09\/ex107.png?resize=1400%2C800 4x"},"classes":[]}],"_links":{"self":[{"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/posts\/1032","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/comments?post=1032"}],"version-history":[{"count":0,"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/posts\/1032\/revisions"}],"wp:attachment":[{"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/media?parent=1032"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/categories?post=1032"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gantovnik.com\/bio-tips\/wp-json\/wp\/v2\/tags?post=1032"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}