How to include data as one group, when plotting separate groups in seaborn
Question:
I have a data frame, and I have to compare a column’s median that has specific values from my dataframe (filtered), with the same column’s median that has all the values in my original dataframe.
Here’s the furthest I have reached, I have presented two graphs, which in my opinion should be in the same graph:
My goal is to merge these two graphs together in one graph.
Here’s my code that gave that output.
filt_waterfront = df['waterfront'] == 1
fig, axs = plt.subplots(1,2)
sns.boxplot(y='price', data = df[filt_waterfront], ax=axs[0], color= 'red')
sns.boxplot(y='price', data = df, ax=axs[1], color = 'orange')
fig.set_size_inches(9,6)
fig.suptitle('Price plots of properties with waterfront and general properties')
fig.axes[1].set_ylabel("Price")
fig.axes[0].set_ylabel("Price")
fig.axes[1].set_xlabel("General Properties")
fig.axes[0].set_xlabel("Properties with Waterfront") <br>
Where my filter is properties having waterfront, the graph on the right shows general properties, which means the original column, and on the left with the filter, I’m trying to find a way to get both of these graph into one graph (because it would look much cleaner and there’s no real reason to present two graphs other than me failing to do it).
Any help is really appreciated, thanks in advance!
Answers:
Use the hue property of the boxplot:
sns.boxplot(y='price', data = meters_df, ax=axs[1], color = 'orange', hue=filt_waterfront)
- The easiest way, which doesn’t deal with manually creating an x-axis and assigning different boxplots, is to create a separate DataFrame with all the data labeled in accordance with the desired labels for the x-axis.
- If you don’t want both original categories, filter out the desired data to use:
filtered = df[['price', 'waterfront']][df.waterfront.eq(1)].copy()
- The following example uses the sample DataFrame from the OP, which has many columns.
comb is created by selecting the specific columns to be plotted, to prevent creating a potentially large DataFrame with unnecessary information.
- If the DataFrame already only has required columns, then use
comb = df.assign(waterfront="All")
- Tested in
python 3.11, pandas 1.5.3, matplotlib 3.7.0, seaborn 0.12.2
import pandas as pd
import seaborn as sns
# Using the sample data from the OP, which has many columns
# Create a copy of the columns to plot and all rows, with waterfront as "All"
comb = df[['price']].assign(waterfront="All")
# combine it to the original columns with the original categories
comb = pd.concat([df[['price', 'waterfront']], comb], ignore_index=True)
# plot
ax = sns.boxplot(data=comb, y='price', x='waterfront')
comb.head()
price waterfront
0 221900.0 0
1 538000.0 1
2 180000.0 0
3 604000.0 1
4 510000.0 0
comb.tail()
price waterfront
95 488000.0 All
96 210490.0 All
97 785000.0 All
98 450000.0 All
99 1350000.0 All
Sample Data
data = {'id': [7129300520, 6414100192, 5631500400, 2487200875, 1954400510, 7237550310, 1321400060, 2008000270, 2414600126, 3793500160, 1736800520, 9212900260, 114101516, 6054650070, 1175000570, 9297300055, 1875500060, 6865200140, 16000397, 7983200060, 6300500875, 2524049179, 7137970340, 8091400200, 3814700200, 1202000200, 1794500383, 3303700376, 5101402488, 1873100390, 8562750320, 2426039314, 461000390, 7589200193, 7955080270, 9547205180, 9435300030, 2768000400, 7895500070, 2078500320, 5547700270, 7766200013, 7203220400, 9270200160, 1432701230, 8035350320, 8945200830, 4178300310, 9215400105, 822039084], 'date': ['20141013T000000', '20141209T000000', '20150225T000000', '20141209T000000', '20150218T000000', '20140512T000000', '20140627T000000', '20150115T000000', '20150415T000000', '20150312T000000', '20150403T000000', '20140527T000000', '20140528T000000', '20141007T000000', '20150312T000000', '20150124T000000', '20140731T000000', '20140529T000000', '20141205T000000', '20150424T000000', '20140514T000000', '20140826T000000', '20140703T000000', '20140516T000000', '20141120T000000', '20141103T000000', '20140626T000000', '20141201T000000', '20140624T000000', '20150302T000000', '20141110T000000', '20141201T000000', '20140624T000000', '20141110T000000', '20141203T000000', '20140613T000000', '20140528T000000', '20141230T000000', '20150213T000000', '20140620T000000', '20140715T000000', '20140811T000000', '20140707T000000', '20141028T000000', '20140729T000000', '20140718T000000', '20150325T000000', '20140716T000000', '20150428T000000', '20150311T000000'], 'price': [221900.0, 538000.0, 180000.0, 604000.0, 510000.0, 1225000.0, 257500.0, 291850.0, 229500.0, 323000.0, 662500.0, 468000.0, 310000.0, 400000.0, 530000.0, 650000.0, 395000.0, 485000.0, 189000.0, 230000.0, 385000.0, 2000000.0, 285000.0, 252700.0, 329000.0, 233000.0, 937000.0, 667000.0, 438000.0, 719000.0, 580500.0, 280000.0, 687500.0, 535000.0, 322500.0, 696000.0, 550000.0, 640000.0, 240000.0, 605000.0, 625000.0, 775000.0, 861990.0, 685000.0, 309000.0, 488000.0, 210490.0, 785000.0, 450000.0, 1350000.0], 'bedrooms': [3, 3, 2, 4, 3, 4, 3, 3, 3, 3, 3, 2, 3, 3, 5, 4, 3, 4, 2, 3, 4, 3, 5, 2, 3, 3, 3, 3, 3, 4, 3, 2, 4, 3, 4, 3, 4, 4, 4, 4, 4, 4, 5, 3, 3, 3, 3, 4, 3, 3], 'bathrooms': [1.0, 2.25, 1.0, 3.0, 2.0, 4.5, 2.25, 1.5, 1.0, 2.5, 2.5, 1.0, 1.0, 1.75, 2.0, 3.0, 2.0, 1.0, 1.0, 1.0, 1.75, 2.75, 2.5, 1.5, 2.25, 2.0, 1.75, 1.0, 1.75, 2.5, 2.5, 1.5, 1.75, 1.0, 2.75, 2.5, 1.0, 2.0, 1.0, 2.5, 2.5, 2.25, 2.75, 1.0, 1.0, 2.5, 1.0, 2.5, 1.75, 2.5], 'sqmeters_living': [109.624675, 238.758826, 71.534745, 182.088443, 156.075808, 503.530286, 159.327388, 98.476403, 165.366035, 175.585284, 330.73207, 107.76663, 132.850242, 127.276106, 168.153103, 274.061687, 175.585284, 148.643627, 111.48272, 116.127834, 150.501672, 283.351914, 210.888146, 99.405425, 227.610554, 158.862876, 227.610554, 130.063174, 141.211446, 238.758826, 215.533259, 110.553698, 216.462282, 101.263471, 191.37867, 213.675214, 154.217763, 219.24935, 113.340766, 243.403939, 238.758826, 392.047566, 333.983649, 145.856559, 118.914902, 293.571163, 91.973244, 212.746191, 116.127834, 255.759941], 'sqmeters_lot': [524.897808, 672.798216, 929.022668, 464.511334, 750.650316, 9469.528056, 633.500557, 902.173913, 693.979933, 609.43887, 910.070606, 557.413601, 1848.848012, 899.293943, 450.575994, 464.511334, 1304.347826, 399.479747, 915.087328, 908.026756, 462.653289, 4168.246005, 585.284281, 895.856559, 603.864734, 436.361947, 250.0, 146.878484, 592.716462, 666.38796, 369.751022, 117.521368, 464.511334, 278.7068, 618.636195, 284.280936, 3237.458194, 557.413601, 750.185805, 701.690821, 512.820513, 2246.934225, 523.875883, 211.817168, 897.064288, 1263.749535, 792.270531, 1246.376812, 553.976217, 6039.111854], 'floors': [1.0, 2.0, 1.0, 1.0, 1.0, 1.0, 2.0, 1.0, 1.0, 2.0, 1.0, 1.0, 1.5, 1.0, 1.5, 2.0, 2.0, 1.5, 1.0, 1.0, 1.0, 1.0, 2.0, 1.0, 2.0, 1.5, 2.0, 1.5, 1.0, 2.0, 2.0, 3.0, 1.5, 1.5, 1.0, 1.5, 1.0, 2.0, 1.0, 2.0, 2.0, 1.0, 2.0, 2.0, 1.0, 2.0, 1.0, 2.0, 1.0, 1.0], 'waterfront': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1], 'view': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2], 'grade': [7, 7, 6, 7, 8, 11, 7, 7, 7, 7, 8, 7, 7, 7, 7, 9, 7, 7, 7, 7, 7, 9, 8, 7, 8, 6, 8, 8, 7, 8, 8, 7, 7, 8, 7, 8, 5, 8, 7, 8, 9, 8, 9, 7, 6, 8, 6, 9, 7, 9], 'sqmeters_above': [109.624675, 201.597919, 71.534745, 97.54738, 156.075808, 361.389818, 159.327388, 98.476403, 97.54738, 175.585284, 172.798216, 79.895949, 132.850242, 127.276106, 168.153103, 183.946488, 175.585284, 148.643627, 111.48272, 116.127834, 79.895949, 216.462282, 210.888146, 99.405425, 227.610554, 158.862876, 162.578967, 130.063174, 73.392791, 238.758826, 215.533259, 110.553698, 140.282423, 101.263471, 118.914902, 140.282423, 86.399108, 219.24935, 82.683017, 243.403939, 238.758826, 241.545894, 333.983649, 145.856559, 85.470085, 293.571163, 91.973244, 212.746191, 116.127834, 201.133408], 'sqmeters_basement': [0.0, 37.160907, 0.0, 84.541063, 0.0, 142.140468, 0.0, 0.0, 67.818655, 0.0, 157.933854, 27.87068, 0.0, 0.0, 0.0, 90.115199, 0.0, 0.0, 0.0, 0.0, 70.605723, 66.889632, 0.0, 0.0, 0.0, 0.0, 65.031587, 0.0, 67.818655, 0.0, 0.0, 0.0, 76.179859, 0.0, 72.463768, 73.392791, 67.818655, 0.0, 30.657748, 0.0, 0.0, 150.501672, 0.0, 0.0, 33.444816, 0.0, 0.0, 0.0, 0.0, 0.0], 'yr_built': [1955.0, 1951.0, 1933.0, 1965.0, 1987.0, 2001.0, 1995.0, 1963.0, 1960.0, 2003.0, 1965.0, 1942.0, 1927.0, 1977.0, 1900.0, 1979.0, 1994.0, 1916.0, 1921.0, 1969.0, 1947.0, 1968.0, 1995.0, 1985.0, 1985.0, 1941.0, 1915.0, 1909.0, 1948.0, 2005.0, 2003.0, 2005.0, 1929.0, 1929.0, 1981.0, 1930.0, 1933.0, 1904.0, 1969.0, 1996.0, 2000.0, 1984.0, 2014.0, 1922.0, 1959.0, 2003.0, 1966.0, 1981.0, 1953.0, 0.0], 'yr_renovated': [0.0, 1991.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2002.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0], 'zipcode': [98178.0, 98125.0, 98028.0, 98136.0, 98074.0, 98053.0, 98003.0, 98198.0, 98146.0, 98038.0, 98007.0, 98115.0, 98028.0, 98074.0, 98107.0, 98126.0, 98019.0, 98103.0, 98002.0, 98003.0, 98133.0, 98040.0, 98092.0, 98030.0, 98030.0, 98002.0, 98119.0, 98112.0, 98115.0, 98052.0, 98027.0, 98133.0, 98117.0, 98117.0, 98058.0, 98115.0, 98052.0, 98107.0, 98001.0, 98056.0, 98074.0, 98166.0, 98053.0, 98119.0, 98058.0, 98019.0, 98023.0, 98007.0, 98115.0, 0.0], 'lat': [47.5112, 47.721, 47.7379, 47.5208, 47.6168, 47.6561, 47.3097, 47.4095, 47.5123, 47.3684, 47.6007, 47.69, 47.7558, 47.6127, 47.67, 47.5714, 47.7277, 47.6648, 47.3089, 47.3343, 47.7025, 47.5316, 47.3266, 47.3533, 47.3739, 47.3048, 47.6386, 47.6221, 47.695, 47.7073, 47.5391, 47.7274, 47.6823, 47.6889, 47.4276, 47.6827, 47.6621, 47.6702, 47.3341, 47.5301, 47.6145, 47.445, 47.6848, 47.6413, 47.4485, 47.7443, 47.3066, 47.6194, 47.6796, 0.0], 'long': [-122.257, -122.319, -122.233, -122.393, -122.045, -122.005, -122.327, -122.315, -122.337, -122.031, -122.145, -122.292, -122.229, -122.045, -122.394, -122.375, -121.962, -122.343, -122.21, -122.306, -122.341, -122.233, -122.169, -122.166, -122.172, -122.218, -122.36, -122.314, -122.304, -122.11, -122.07, -122.357, -122.368, -122.375, -122.157, -122.31, -122.132, -122.362, -122.282, -122.18, -122.027, -122.347, -122.016, -122.364, -122.175, -121.977, -122.371, -122.151, -122.301, 0.0], 'sqmeters_living15': [124.489038, 157.004831, 252.694166, 126.347083, 167.22408, 442.21479, 207.915273, 153.28874, 165.366035, 222.036418, 205.31401, 123.560015, 165.366035, 127.276106, 126.347083, 198.810851, 175.585284, 149.57265, 98.476403, 118.914902, 130.063174, 381.828317, 208.101078, 113.340766, 204.384987, 95.689335, 163.50799, 172.798216, 141.211446, 244.332962, 239.687848, 129.134151, 135.63731, 145.856559, 187.662579, 147.714604, 200.668896, 160.720922, 119.843924, 243.403939, 229.468599, 223.894463, 336.770717, 146.785582, 124.489038, 283.351914, 114.083984, 248.978075, 90.115199, 0.0], 'sqmeters_lot15': [524.897808, 709.680416, 748.978075, 464.511334, 697.045708, 9469.528056, 633.500557, 902.173913, 753.716091, 703.27016, 829.152731, 557.413601, 1179.580082, 948.34634, 450.575994, 371.609067, 1302.303976, 399.479747, 473.337049, 822.185061, 462.653289, 1889.260498, 650.780379, 779.07841, 637.774062, 437.105165, 331.939799, 358.695652, 579.245634, 559.82906, 369.751022, 163.136381, 464.511334, 471.943515, 810.107767, 303.232999, 1065.310294, 436.640654, 724.637681, 1104.050539, 526.662951, 2844.388703, 523.875883, 245.261984, 818.283166, 857.673727, 821.256039, 1271.367521, 473.801561, 0.0]}
df = pd.DataFrame(data)
# display(df[['price', 'waterfront']].head())
price waterfront
0 221900.0 0
1 538000.0 1
2 180000.0 0
3 604000.0 1
4 510000.0 0
I have a data frame, and I have to compare a column’s median that has specific values from my dataframe (filtered), with the same column’s median that has all the values in my original dataframe.
Here’s the furthest I have reached, I have presented two graphs, which in my opinion should be in the same graph:
My goal is to merge these two graphs together in one graph.
Here’s my code that gave that output.
filt_waterfront = df['waterfront'] == 1
fig, axs = plt.subplots(1,2)
sns.boxplot(y='price', data = df[filt_waterfront], ax=axs[0], color= 'red')
sns.boxplot(y='price', data = df, ax=axs[1], color = 'orange')
fig.set_size_inches(9,6)
fig.suptitle('Price plots of properties with waterfront and general properties')
fig.axes[1].set_ylabel("Price")
fig.axes[0].set_ylabel("Price")
fig.axes[1].set_xlabel("General Properties")
fig.axes[0].set_xlabel("Properties with Waterfront") <br>
Where my filter is properties having waterfront, the graph on the right shows general properties, which means the original column, and on the left with the filter, I’m trying to find a way to get both of these graph into one graph (because it would look much cleaner and there’s no real reason to present two graphs other than me failing to do it).
Any help is really appreciated, thanks in advance!
Use the hue property of the boxplot:
sns.boxplot(y='price', data = meters_df, ax=axs[1], color = 'orange', hue=filt_waterfront)
- The easiest way, which doesn’t deal with manually creating an x-axis and assigning different boxplots, is to create a separate DataFrame with all the data labeled in accordance with the desired labels for the x-axis.
- If you don’t want both original categories, filter out the desired data to use:
filtered = df[['price', 'waterfront']][df.waterfront.eq(1)].copy()
- The following example uses the sample DataFrame from the OP, which has many columns.
combis created by selecting the specific columns to be plotted, to prevent creating a potentially large DataFrame with unnecessary information.- If the DataFrame already only has required columns, then use
comb = df.assign(waterfront="All")
- If the DataFrame already only has required columns, then use
- Tested in
python 3.11,pandas 1.5.3,matplotlib 3.7.0,seaborn 0.12.2
import pandas as pd
import seaborn as sns
# Using the sample data from the OP, which has many columns
# Create a copy of the columns to plot and all rows, with waterfront as "All"
comb = df[['price']].assign(waterfront="All")
# combine it to the original columns with the original categories
comb = pd.concat([df[['price', 'waterfront']], comb], ignore_index=True)
# plot
ax = sns.boxplot(data=comb, y='price', x='waterfront')
comb.head()
price waterfront
0 221900.0 0
1 538000.0 1
2 180000.0 0
3 604000.0 1
4 510000.0 0
comb.tail()
price waterfront
95 488000.0 All
96 210490.0 All
97 785000.0 All
98 450000.0 All
99 1350000.0 All
Sample Data
data = {'id': [7129300520, 6414100192, 5631500400, 2487200875, 1954400510, 7237550310, 1321400060, 2008000270, 2414600126, 3793500160, 1736800520, 9212900260, 114101516, 6054650070, 1175000570, 9297300055, 1875500060, 6865200140, 16000397, 7983200060, 6300500875, 2524049179, 7137970340, 8091400200, 3814700200, 1202000200, 1794500383, 3303700376, 5101402488, 1873100390, 8562750320, 2426039314, 461000390, 7589200193, 7955080270, 9547205180, 9435300030, 2768000400, 7895500070, 2078500320, 5547700270, 7766200013, 7203220400, 9270200160, 1432701230, 8035350320, 8945200830, 4178300310, 9215400105, 822039084], 'date': ['20141013T000000', '20141209T000000', '20150225T000000', '20141209T000000', '20150218T000000', '20140512T000000', '20140627T000000', '20150115T000000', '20150415T000000', '20150312T000000', '20150403T000000', '20140527T000000', '20140528T000000', '20141007T000000', '20150312T000000', '20150124T000000', '20140731T000000', '20140529T000000', '20141205T000000', '20150424T000000', '20140514T000000', '20140826T000000', '20140703T000000', '20140516T000000', '20141120T000000', '20141103T000000', '20140626T000000', '20141201T000000', '20140624T000000', '20150302T000000', '20141110T000000', '20141201T000000', '20140624T000000', '20141110T000000', '20141203T000000', '20140613T000000', '20140528T000000', '20141230T000000', '20150213T000000', '20140620T000000', '20140715T000000', '20140811T000000', '20140707T000000', '20141028T000000', '20140729T000000', '20140718T000000', '20150325T000000', '20140716T000000', '20150428T000000', '20150311T000000'], 'price': [221900.0, 538000.0, 180000.0, 604000.0, 510000.0, 1225000.0, 257500.0, 291850.0, 229500.0, 323000.0, 662500.0, 468000.0, 310000.0, 400000.0, 530000.0, 650000.0, 395000.0, 485000.0, 189000.0, 230000.0, 385000.0, 2000000.0, 285000.0, 252700.0, 329000.0, 233000.0, 937000.0, 667000.0, 438000.0, 719000.0, 580500.0, 280000.0, 687500.0, 535000.0, 322500.0, 696000.0, 550000.0, 640000.0, 240000.0, 605000.0, 625000.0, 775000.0, 861990.0, 685000.0, 309000.0, 488000.0, 210490.0, 785000.0, 450000.0, 1350000.0], 'bedrooms': [3, 3, 2, 4, 3, 4, 3, 3, 3, 3, 3, 2, 3, 3, 5, 4, 3, 4, 2, 3, 4, 3, 5, 2, 3, 3, 3, 3, 3, 4, 3, 2, 4, 3, 4, 3, 4, 4, 4, 4, 4, 4, 5, 3, 3, 3, 3, 4, 3, 3], 'bathrooms': [1.0, 2.25, 1.0, 3.0, 2.0, 4.5, 2.25, 1.5, 1.0, 2.5, 2.5, 1.0, 1.0, 1.75, 2.0, 3.0, 2.0, 1.0, 1.0, 1.0, 1.75, 2.75, 2.5, 1.5, 2.25, 2.0, 1.75, 1.0, 1.75, 2.5, 2.5, 1.5, 1.75, 1.0, 2.75, 2.5, 1.0, 2.0, 1.0, 2.5, 2.5, 2.25, 2.75, 1.0, 1.0, 2.5, 1.0, 2.5, 1.75, 2.5], 'sqmeters_living': [109.624675, 238.758826, 71.534745, 182.088443, 156.075808, 503.530286, 159.327388, 98.476403, 165.366035, 175.585284, 330.73207, 107.76663, 132.850242, 127.276106, 168.153103, 274.061687, 175.585284, 148.643627, 111.48272, 116.127834, 150.501672, 283.351914, 210.888146, 99.405425, 227.610554, 158.862876, 227.610554, 130.063174, 141.211446, 238.758826, 215.533259, 110.553698, 216.462282, 101.263471, 191.37867, 213.675214, 154.217763, 219.24935, 113.340766, 243.403939, 238.758826, 392.047566, 333.983649, 145.856559, 118.914902, 293.571163, 91.973244, 212.746191, 116.127834, 255.759941], 'sqmeters_lot': [524.897808, 672.798216, 929.022668, 464.511334, 750.650316, 9469.528056, 633.500557, 902.173913, 693.979933, 609.43887, 910.070606, 557.413601, 1848.848012, 899.293943, 450.575994, 464.511334, 1304.347826, 399.479747, 915.087328, 908.026756, 462.653289, 4168.246005, 585.284281, 895.856559, 603.864734, 436.361947, 250.0, 146.878484, 592.716462, 666.38796, 369.751022, 117.521368, 464.511334, 278.7068, 618.636195, 284.280936, 3237.458194, 557.413601, 750.185805, 701.690821, 512.820513, 2246.934225, 523.875883, 211.817168, 897.064288, 1263.749535, 792.270531, 1246.376812, 553.976217, 6039.111854], 'floors': [1.0, 2.0, 1.0, 1.0, 1.0, 1.0, 2.0, 1.0, 1.0, 2.0, 1.0, 1.0, 1.5, 1.0, 1.5, 2.0, 2.0, 1.5, 1.0, 1.0, 1.0, 1.0, 2.0, 1.0, 2.0, 1.5, 2.0, 1.5, 1.0, 2.0, 2.0, 3.0, 1.5, 1.5, 1.0, 1.5, 1.0, 2.0, 1.0, 2.0, 2.0, 1.0, 2.0, 2.0, 1.0, 2.0, 1.0, 2.0, 1.0, 1.0], 'waterfront': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1], 'view': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2], 'grade': [7, 7, 6, 7, 8, 11, 7, 7, 7, 7, 8, 7, 7, 7, 7, 9, 7, 7, 7, 7, 7, 9, 8, 7, 8, 6, 8, 8, 7, 8, 8, 7, 7, 8, 7, 8, 5, 8, 7, 8, 9, 8, 9, 7, 6, 8, 6, 9, 7, 9], 'sqmeters_above': [109.624675, 201.597919, 71.534745, 97.54738, 156.075808, 361.389818, 159.327388, 98.476403, 97.54738, 175.585284, 172.798216, 79.895949, 132.850242, 127.276106, 168.153103, 183.946488, 175.585284, 148.643627, 111.48272, 116.127834, 79.895949, 216.462282, 210.888146, 99.405425, 227.610554, 158.862876, 162.578967, 130.063174, 73.392791, 238.758826, 215.533259, 110.553698, 140.282423, 101.263471, 118.914902, 140.282423, 86.399108, 219.24935, 82.683017, 243.403939, 238.758826, 241.545894, 333.983649, 145.856559, 85.470085, 293.571163, 91.973244, 212.746191, 116.127834, 201.133408], 'sqmeters_basement': [0.0, 37.160907, 0.0, 84.541063, 0.0, 142.140468, 0.0, 0.0, 67.818655, 0.0, 157.933854, 27.87068, 0.0, 0.0, 0.0, 90.115199, 0.0, 0.0, 0.0, 0.0, 70.605723, 66.889632, 0.0, 0.0, 0.0, 0.0, 65.031587, 0.0, 67.818655, 0.0, 0.0, 0.0, 76.179859, 0.0, 72.463768, 73.392791, 67.818655, 0.0, 30.657748, 0.0, 0.0, 150.501672, 0.0, 0.0, 33.444816, 0.0, 0.0, 0.0, 0.0, 0.0], 'yr_built': [1955.0, 1951.0, 1933.0, 1965.0, 1987.0, 2001.0, 1995.0, 1963.0, 1960.0, 2003.0, 1965.0, 1942.0, 1927.0, 1977.0, 1900.0, 1979.0, 1994.0, 1916.0, 1921.0, 1969.0, 1947.0, 1968.0, 1995.0, 1985.0, 1985.0, 1941.0, 1915.0, 1909.0, 1948.0, 2005.0, 2003.0, 2005.0, 1929.0, 1929.0, 1981.0, 1930.0, 1933.0, 1904.0, 1969.0, 1996.0, 2000.0, 1984.0, 2014.0, 1922.0, 1959.0, 2003.0, 1966.0, 1981.0, 1953.0, 0.0], 'yr_renovated': [0.0, 1991.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 2002.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0], 'zipcode': [98178.0, 98125.0, 98028.0, 98136.0, 98074.0, 98053.0, 98003.0, 98198.0, 98146.0, 98038.0, 98007.0, 98115.0, 98028.0, 98074.0, 98107.0, 98126.0, 98019.0, 98103.0, 98002.0, 98003.0, 98133.0, 98040.0, 98092.0, 98030.0, 98030.0, 98002.0, 98119.0, 98112.0, 98115.0, 98052.0, 98027.0, 98133.0, 98117.0, 98117.0, 98058.0, 98115.0, 98052.0, 98107.0, 98001.0, 98056.0, 98074.0, 98166.0, 98053.0, 98119.0, 98058.0, 98019.0, 98023.0, 98007.0, 98115.0, 0.0], 'lat': [47.5112, 47.721, 47.7379, 47.5208, 47.6168, 47.6561, 47.3097, 47.4095, 47.5123, 47.3684, 47.6007, 47.69, 47.7558, 47.6127, 47.67, 47.5714, 47.7277, 47.6648, 47.3089, 47.3343, 47.7025, 47.5316, 47.3266, 47.3533, 47.3739, 47.3048, 47.6386, 47.6221, 47.695, 47.7073, 47.5391, 47.7274, 47.6823, 47.6889, 47.4276, 47.6827, 47.6621, 47.6702, 47.3341, 47.5301, 47.6145, 47.445, 47.6848, 47.6413, 47.4485, 47.7443, 47.3066, 47.6194, 47.6796, 0.0], 'long': [-122.257, -122.319, -122.233, -122.393, -122.045, -122.005, -122.327, -122.315, -122.337, -122.031, -122.145, -122.292, -122.229, -122.045, -122.394, -122.375, -121.962, -122.343, -122.21, -122.306, -122.341, -122.233, -122.169, -122.166, -122.172, -122.218, -122.36, -122.314, -122.304, -122.11, -122.07, -122.357, -122.368, -122.375, -122.157, -122.31, -122.132, -122.362, -122.282, -122.18, -122.027, -122.347, -122.016, -122.364, -122.175, -121.977, -122.371, -122.151, -122.301, 0.0], 'sqmeters_living15': [124.489038, 157.004831, 252.694166, 126.347083, 167.22408, 442.21479, 207.915273, 153.28874, 165.366035, 222.036418, 205.31401, 123.560015, 165.366035, 127.276106, 126.347083, 198.810851, 175.585284, 149.57265, 98.476403, 118.914902, 130.063174, 381.828317, 208.101078, 113.340766, 204.384987, 95.689335, 163.50799, 172.798216, 141.211446, 244.332962, 239.687848, 129.134151, 135.63731, 145.856559, 187.662579, 147.714604, 200.668896, 160.720922, 119.843924, 243.403939, 229.468599, 223.894463, 336.770717, 146.785582, 124.489038, 283.351914, 114.083984, 248.978075, 90.115199, 0.0], 'sqmeters_lot15': [524.897808, 709.680416, 748.978075, 464.511334, 697.045708, 9469.528056, 633.500557, 902.173913, 753.716091, 703.27016, 829.152731, 557.413601, 1179.580082, 948.34634, 450.575994, 371.609067, 1302.303976, 399.479747, 473.337049, 822.185061, 462.653289, 1889.260498, 650.780379, 779.07841, 637.774062, 437.105165, 331.939799, 358.695652, 579.245634, 559.82906, 369.751022, 163.136381, 464.511334, 471.943515, 810.107767, 303.232999, 1065.310294, 436.640654, 724.637681, 1104.050539, 526.662951, 2844.388703, 523.875883, 245.261984, 818.283166, 857.673727, 821.256039, 1271.367521, 473.801561, 0.0]}
df = pd.DataFrame(data)
# display(df[['price', 'waterfront']].head())
price waterfront
0 221900.0 0
1 538000.0 1
2 180000.0 0
3 604000.0 1
4 510000.0 0