Area Analysis

import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns

df = pd.read_csv('graphql_master.csv') len(df)

df.columns

df.describe()

w_area = df.query('area > 1')

w_area['log_area'] = np.log(w_area.area) w_area['log_hammer'] = np.log(w_area.hammer_price)

/shared-libs/python3.7/py-core/lib/python3.7/site-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  """Entry point for launching an IPython kernel.
/shared-libs/python3.7/py/lib/python3.7/site-packages/pandas/core/arraylike.py:358: RuntimeWarning: invalid value encountered in log
  result = getattr(ufunc, method)(*inputs, **kwargs)
/shared-libs/python3.7/py-core/lib/python3.7/site-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy

top_names = w_area.groupby('name')['medium'].count().sort_values().iloc[-100:].index top_artist_area = w_area[w_area['name'].isin(top_names)]

corr_func = lambda df: df['log_hammer'].corr(df['log_area']) top_artist_corr = top_artist_area.groupby('name').apply(corr_func).sort_values(ascending=False) top_artist_corr

def view_artist(df, artist_name): df = df.query(f'name == "{artist_name}"') df.plot.scatter('log_area','log_hammer') plt.title(f'{artist_name}') plt.show()

view_artist(top_artist_area, 'Henry Moore')

view_artist(top_artist_area, 'André Kertész')

view_artist(top_artist_area, 'Diane Arbus')

view_artist(top_artist_area, 'Fernando Botero')

view_artist(top_artist_area, 'Camille Pissarro')

view_artist(top_artist_area, 'Thomas Ruff')

data = top_artist_area.query('name == "Camille Pissarro"').dropna() x = data.log_area.values y = data.log_hammer.values np.polyfit(x, y, 2)

ax = sns.histplot(top_artist_corr).set(title='Histogram of Correlations')

ax = sns.countplot(x=pd.cut(top_artist_corr, bins=[0,0.3,0.6,1])).set(title='Percent of Artists with Positive Effect by Correlation')

f,ax = plt.subplots(figsize=(8,8)) mediums = ['painting', 'drawing', 'print', 'sculpture', 'photograph', 'mixed media'] g = sns.scatterplot('log_area', 'log_hammer', hue='medium', ax=ax, data=w_area[w_area.medium.isin(mediums)])

/shared-libs/python3.7/py/lib/python3.7/site-packages/seaborn/_decorators.py:43: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  FutureWarning

top_painter_names = w_area.query('medium == "painting"').groupby('name')['medium'].count().sort_values().iloc[-500:].index top_painter_area = w_area[w_area['name'].isin(top_painter_names)] top_painter_corr = top_painter_area.groupby('name').apply(corr_func).sort_values(ascending=False) top_painter_corr

ax = sns.countplot(x=pd.cut(top_painter_corr, bins=[0,0.3,0.6,1])).set(title='Count of Works by Correlation')

view_artist(top_painter_area, 'Salvador Dalí')

view_artist(top_painter_area, 'Eliot Hodgkin')

data = top_painter_area.query('name == "Eliot Hodgkin"').dropna() x = data.log_area.values y = data.log_hammer.values np.polyfit(x, y, 2)

view_artist(top_painter_area, 'Elizabeth Peyton')

top_photo_names = w_area.query('medium == "photograph"').groupby('name')['medium'].count().sort_values().iloc[-100:] top_photo_area = w_area[w_area['name'].isin(top_photo_names.index)].query('medium == "photograph"') top_photo_corr = top_photo_area.groupby('name').apply(lambda df: df['log_hammer'].corr(df['log_area'])).sort_values(ascending=False) print(top_photo_names) top_photo_corr

name
Rineke Dijkstra           64
Edward S. Curtis          64
Peter Lindbergh           64
Mario Giacomelli          64
Joel Sternfeld            65
                        ... 
Hiroshi Sugimoto         626
Irving Penn              671
Robert Mapplethorpe      715
Ansel Adams              799
Henri Cartier-Bresson    899
Name: medium, Length: 100, dtype: int64

view_artist(top_photo_area, 'Robert Adams')

## Most prolific photographer in our data view_artist(top_photo_area, 'Henri Cartier-Bresson')

view_artist(top_photo_area, 'Thomas Struth')

df.groupby('medium')['hammer_price'].count().sort_values(ascending=False)

top_painter_corr[200:250]

df.living.describe()

df.living.hist()