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


from matplotlib.font_manager import FontProperties


font = FontProperties(fname="../../simhei.ttf")


GDP = pd.read_csv("../datasets/Chinas GDP in Province Zh.csv",index_col=0)

GDP


GDP.T


GDP.T


plt.figure(figsize=(28,10))
plt.bar(x=GDP.columns.values,height=GDP.iloc[0],width=0.5)
plt.xticks(GDP.columns.values,font=font,rotation=40,fontsize=14)
plt.yticks(fontsize=16)
plt.xlabel("省份",font=font,fontsize=20)
plt.ylabel("GDP",font=font,fontsize=20)
plt.title("2020年GDP情况",font=font,fontsize=20)
plt.show()


help(GDP.iloc)

Help on _iLocIndexer in module pandas.core.indexing object:

class _iLocIndexer(_LocationIndexer)
 |  Purely integer-location based indexing for selection by position.
 |  
 |  ``.iloc[]`` is primarily integer position based (from ``0`` to
 |  ``length-1`` of the axis), but may also be used with a boolean
 |  array.
 |  
 |  Allowed inputs are:
 |  
 |  - An integer, e.g. ``5``.
 |  - A list or array of integers, e.g. ``[4, 3, 0]``.
 |  - A slice object with ints, e.g. ``1:7``.
 |  - A boolean array.
 |  - A ``callable`` function with one argument (the calling Series or
 |    DataFrame) and that returns valid output for indexing (one of the above).
 |    This is useful in method chains, when you don't have a reference to the
 |    calling object, but would like to base your selection on some value.
 |  
 |  ``.iloc`` will raise ``IndexError`` if a requested indexer is
 |  out-of-bounds, except *slice* indexers which allow out-of-bounds
 |  indexing (this conforms with python/numpy *slice* semantics).
 |  
 |  See more at :ref:`Selection by Position <indexing.integer>`.
 |  
 |  See Also
 |  --------
 |  DataFrame.iat : Fast integer location scalar accessor.
 |  DataFrame.loc : Purely label-location based indexer for selection by label.
 |  Series.iloc : Purely integer-location based indexing for
 |                 selection by position.
 |  
 |  Examples
 |  --------
 |  >>> mydict = [{'a': 1, 'b': 2, 'c': 3, 'd': 4},
 |  ...           {'a': 100, 'b': 200, 'c': 300, 'd': 400},
 |  ...           {'a': 1000, 'b': 2000, 'c': 3000, 'd': 4000 }]
 |  >>> df = pd.DataFrame(mydict)
 |  >>> df
 |        a     b     c     d
 |  0     1     2     3     4
 |  1   100   200   300   400
 |  2  1000  2000  3000  4000
 |  
 |  **Indexing just the rows**
 |  
 |  With a scalar integer.
 |  
 |  >>> type(df.iloc[0])
 |  <class 'pandas.core.series.Series'>
 |  >>> df.iloc[0]
 |  a    1
 |  b    2
 |  c    3
 |  d    4
 |  Name: 0, dtype: int64
 |  
 |  With a list of integers.
 |  
 |  >>> df.iloc[[0]]
 |     a  b  c  d
 |  0  1  2  3  4
 |  >>> type(df.iloc[[0]])
 |  <class 'pandas.core.frame.DataFrame'>
 |  
 |  >>> df.iloc[[0, 1]]
 |       a    b    c    d
 |  0    1    2    3    4
 |  1  100  200  300  400
 |  
 |  With a `slice` object.
 |  
 |  >>> df.iloc[:3]
 |        a     b     c     d
 |  0     1     2     3     4
 |  1   100   200   300   400
 |  2  1000  2000  3000  4000
 |  
 |  With a boolean mask the same length as the index.
 |  
 |  >>> df.iloc[[True, False, True]]
 |        a     b     c     d
 |  0     1     2     3     4
 |  2  1000  2000  3000  4000
 |  
 |  With a callable, useful in method chains. The `x` passed
 |  to the ``lambda`` is the DataFrame being sliced. This selects
 |  the rows whose index label even.
 |  
 |  >>> df.iloc[lambda x: x.index % 2 == 0]
 |        a     b     c     d
 |  0     1     2     3     4
 |  2  1000  2000  3000  4000
 |  
 |  **Indexing both axes**
 |  
 |  You can mix the indexer types for the index and columns. Use ``:`` to
 |  select the entire axis.
 |  
 |  With scalar integers.
 |  
 |  >>> df.iloc[0, 1]
 |  2
 |  
 |  With lists of integers.
 |  
 |  >>> df.iloc[[0, 2], [1, 3]]
 |        b     d
 |  0     2     4
 |  2  2000  4000
 |  
 |  With `slice` objects.
 |  
 |  >>> df.iloc[1:3, 0:3]
 |        a     b     c
 |  1   100   200   300
 |  2  1000  2000  3000
 |  
 |  With a boolean array whose length matches the columns.
 |  
 |  >>> df.iloc[:, [True, False, True, False]]
 |        a     c
 |  0     1     3
 |  1   100   300
 |  2  1000  3000
 |  
 |  With a callable function that expects the Series or DataFrame.
 |  
 |  >>> df.iloc[:, lambda df: [0, 2]]
 |        a     c
 |  0     1     3
 |  1   100   300
 |  2  1000  3000
 |  
 |  Method resolution order:
 |      _iLocIndexer
 |      _LocationIndexer
 |      pandas._libs.indexing._NDFrameIndexerBase
 |      builtins.object
 |  
 |  Methods inherited from _LocationIndexer:
 |  
 |  __call__(self, axis=None)
 |      Call self as a function.
 |  
 |  __getitem__(self, key)
 |  
 |  __setitem__(self, key, value)
 |  
 |  ----------------------------------------------------------------------
 |  Data descriptors inherited from _LocationIndexer:
 |  
 |  __dict__
 |      dictionary for instance variables (if defined)
 |  
 |  __weakref__
 |      list of weak references to the object (if defined)
 |  
 |  ----------------------------------------------------------------------
 |  Data and other attributes inherited from _LocationIndexer:
 |  
 |  __annotations__ = {'_valid_types': <class 'str'>}
 |  
 |  axis = None
 |  
 |  ----------------------------------------------------------------------
 |  Methods inherited from pandas._libs.indexing._NDFrameIndexerBase:
 |  
 |  __init__(self, /, *args, **kwargs)
 |      Initialize self.  See help(type(self)) for accurate signature.
 |  
 |  __new__(*args, **kwargs) from builtins.type
 |      Create and return a new object.  See help(type) for accurate signature.
 |  
 |  __reduce__ = __reduce_cython__(...)
 |  
 |  __setstate__ = __setstate_cython__(...)
 |  
 |  ----------------------------------------------------------------------
 |  Data descriptors inherited from pandas._libs.indexing._NDFrameIndexerBase:
 |  
 |  name
 |  
 |  ndim
 |  
 |  obj


taitanic = pd.read_csv("../datasets/taitanic_train.csv")


taitanic.dropna(subset=["Age"],inplace=True)


plt.hist(x=taitanic["Age"],edgecolor="red",bins=20,density=True)
plt.xlabel("年龄",font=font)
plt.title("年龄分布图",font=font)
plt.ylabel("频率",font=font)
plt.show()


def normalFun(x,mu,sigma):
    return np.exp(-((x-mu)**2) / (2*sigma*2)) / (sigma * np.sqrt(2*np.pi))


mean_x = taitanic["Age"].mean()
std_x = taitanic["Age"].std()


x = np.arange(taitanic["Age"].min(), taitanic["Age"].max()+10,1)

x

array([ 0.42,  1.42,  2.42,  3.42,  4.42,  5.42,  6.42,  7.42,  8.42,
        9.42, 10.42, 11.42, 12.42, 13.42, 14.42, 15.42, 16.42, 17.42,
       18.42, 19.42, 20.42, 21.42, 22.42, 23.42, 24.42, 25.42, 26.42,
       27.42, 28.42, 29.42, 30.42, 31.42, 32.42, 33.42, 34.42, 35.42,
       36.42, 37.42, 38.42, 39.42, 40.42, 41.42, 42.42, 43.42, 44.42,
       45.42, 46.42, 47.42, 48.42, 49.42, 50.42, 51.42, 52.42, 53.42,
       54.42, 55.42, 56.42, 57.42, 58.42, 59.42, 60.42, 61.42, 62.42,
       63.42, 64.42, 65.42, 66.42, 67.42, 68.42, 69.42, 70.42, 71.42,
       72.42, 73.42, 74.42, 75.42, 76.42, 77.42, 78.42, 79.42, 80.42,
       81.42, 82.42, 83.42, 84.42, 85.42, 86.42, 87.42, 88.42, 89.42])


y = normalFun(x,mean_x,std_x)

y

array([1.07494290e-08, 2.89458205e-08, 7.53074567e-08, 1.89296133e-07,
       4.59723969e-07, 1.07870874e-06, 2.44547312e-06, 5.35640286e-06,
       1.13353574e-05, 2.31765532e-05, 4.57840411e-05, 8.73838233e-05,
       1.61138608e-04, 2.87091158e-04, 4.94187403e-04, 8.21892789e-04,
       1.32065784e-03, 2.05029854e-03, 3.07535699e-03, 4.45682534e-03,
       6.24032687e-03, 8.44190979e-03, 1.10338156e-02, 1.39335692e-02,
       1.70000689e-02, 2.00396729e-02, 2.28234988e-02, 2.51145534e-02,
       2.67005583e-02, 2.74262777e-02, 2.72185535e-02, 2.60984586e-02,
       2.41777743e-02, 2.16406064e-02, 1.87143255e-02, 1.56361769e-02,
       1.26223034e-02, 9.84460516e-03, 7.41838952e-03, 5.40098050e-03,
       3.79915690e-03, 2.58198370e-03, 1.69539699e-03, 1.07557565e-03,
       6.59268252e-04, 3.90422652e-04, 2.23387824e-04, 1.23491092e-04,
       6.59573824e-05, 3.40363387e-05, 1.69696899e-05, 8.17441384e-06,
       3.80444211e-06, 1.71071232e-06, 7.43215285e-07, 3.11963602e-07,
       1.26515829e-07, 4.95721151e-08, 1.87664306e-08, 6.86400436e-09,
       2.42563287e-09, 8.28179034e-10, 2.73196443e-10, 8.70717940e-11,
       2.68121469e-11, 7.97695850e-12, 2.29295072e-12, 6.36801023e-13,
       1.70869453e-13, 4.42972486e-14, 1.10953426e-14, 2.68507444e-15,
       6.27803289e-16, 1.41821635e-16, 3.09537332e-17, 6.52732483e-18,
       1.32986961e-18, 2.61778842e-19, 4.97865083e-20, 9.14830087e-21,
       1.62413025e-21, 2.78581912e-22, 4.61675279e-23, 7.39217042e-24,
       1.14356003e-24, 1.70921858e-25, 2.46824286e-26, 3.44373576e-27,
       4.64219516e-28, 6.04600655e-29])


plt.hist(x=taitanic["Age"],color="c",edgecolor="r",bins=20,density=True)
plt.plot(x,y,color="r",linewidth=3,label="正态分布图")
plt.xlabel("年龄",font=font)
plt.title("年龄分布图",font=font)
plt.ylabel("频率",font=font)
plt.show()


plt.hist(x=taitanic["Age"],color="c",edgecolor="r",bins=20,density=True,label="直方分布图")
taitanic["Age"].plot(kind="kde",color="r",linewidth=3,xlim=[0,90],label="核密度图")
plt.plot(x,y,color="blue",linewidth=3,label="正态分布图")
plt.xlabel("年龄",font=font)
plt.title("年龄分布图",font=font)
plt.ylabel("频率",font=font)
plt.legend(loc="best",prop=font) #设置字体
plt.show()


sec_house = pd.read_csv("../datasets/house.csv")


plt.figure(figsize=(10,16))
plt.boxplot(x=sec_house["均价"],showmeans=True,showfliers=True)
plt.title("二手房箱线图",font=font)
plt.show()


iris = pd.read_csv("../datasets/iris.data.txt")


iris


plt.scatter(x=iris.petal_width,y=iris.petal_length)
plt.xlabel("花瓣宽度",font=font)
plt.ylabel("花瓣长度",font=font)
plt.title("鸢尾花花瓣长宽之间的关系",font=font)
plt.show()


color_iris = ['b','r','g']
species=["setosa","virginica","versicolor"]
marker_iris = ["o","s","x"]


iris.petal_width

0      0.2
1      0.2
2      0.2
3      0.2
4      0.2
      ... 
145    2.3
146    1.9
147    2.0
148    2.3
149    1.8
Name: petal_width, Length: 150, dtype: float64


for i in range(3):
    plt.scatter(x = iris.petal_width[iris["species"]==species[i]],
               y = iris.petal_length[iris["species"]==species[i]],
                marker=marker_iris[i],
                color=color_iris[i])
plt.ylabel("花瓣长度",font=font)
plt.title("鸢尾花花瓣长宽之间的关系",font=font)
plt.show()


iris["species"].value_counts()

versicolor    50
setosa        50
virginica     50
Name: species, dtype: int64


GDP_new= GDP.reset_index()


GDP_new.sort_values(by="index",inplace=True)


plt.figure(figsize=(8,7))
plt.plot(
    GDP_new["index"],GDP_new["北京市"],'bs--',
    GDP_new["index"],GDP_new["天津市"],'rs--',
    GDP_new["index"],GDP_new["上海市"],'gs--',
    GDP_new["index"],GDP_new["重庆市"],'cs--',
)

plt.legend(labels=['北京市','天津市','上海市','重庆市'],loc="best",prop=font)
plt.xlabel("年份",font=font)
plt.ylabel("GDP",font=font)
plt.title("不同直辖市GDP的变化",font=font)
plt.show()


sec_house


sec_house.columns

Index(['价格', '小区', '房屋户型', '建筑面积', '户型结构', '建筑类型', '房屋朝向', '建筑结构', '装修情况',
       '梯户比例', '配备电梯', '挂牌时间', '交易权属', '上次交易', '房屋用途', '房屋年限', '产权所有', '区',
       '镇', '环', '室', '厅', '厨', '卫', '所处楼层', '总层数', '有无抵押', '抵押情况', '均价'],
      dtype='object')


sec_house_1 = sec_house.groupby("区")[["价格","均价"]].mean()


sec_house_1["均价"] =sec_house_1["均价"]/10000


sec_house_1


fig=plt.figure(figsize=(9,6))
ax1 = fig.add_subplot(111)
ax1.plot(sec_house_1.index,sec_house_1["价格"],"bs-",label="价格")
ax1.set_ylabel("不同地区的总价",font=font)
# plt.legend(loc="upper left",prop=font)
plt.xticks(sec_house_1.index,font=font,rotation=40)
ax2 = ax1.twinx()
ax2.plot(sec_house_1.index,sec_house_1["均价"],"ro-",label="均价")
ax2.set_ylabel("不同地区的均价",font=font)
fig.legend(labels=('价格','均价'),prop=font)
plt.title("不用地区总价与均价的折线图",font=font)
plt.show()

	北京市	天津市	河北省	山西省	内蒙古自治区	辽宁省	吉林省	黑龙江省	上海市	江苏省	...	重庆市	四川省	贵州省	云南省	西藏自治区	陕西省	甘肃省	青海省	宁夏回族自治区	新疆维吾尔自治区
2020	36102.6	14083.7	36206.9	17651.9	17359.8	25115.0	12311.3	13698.5	38700.6	102719.0	...	25002.8	48598.8	17826.6	24521.9	1902.7	26181.9	9016.7	3005.9	3920.6	13797.6
2019	35445.1	14055.5	34978.6	16961.6	17212.5	24855.3	11726.8	13544.4	37987.6	98656.8	...	23605.8	46363.8	16769.3	23223.8	1697.8	25793.2	8718.3	2941.1	3748.5	13597.1
2018	33106.0	13362.9	32494.6	15958.1	16140.8	23510.5	11253.8	12846.5	36011.8	93207.6	...	21588.8	42902.1	15353.2	20880.6	1548.4	23941.9	8104.1	2748.0	3510.2	12809.4
2017	29883.0	12450.6	30640.8	14484.3	14898.1	21693.0	10922.0	12313.0	32925.0	85869.8	...	20066.3	37905.1	13605.4	18486.0	1349.0	21473.5	7336.7	2465.1	3200.3	11159.9
2016	27041.2	11477.2	28474.1	11946.4	13789.3	20392.5	10427.0	11895.0	29887.0	77350.9	...	18023.0	33138.5	11792.4	16369.0	1173.0	19045.8	6907.9	2258.2	2781.4	9630.8
2015	24779.1	10879.5	26398.4	11836.4	12949.0	20210.3	10018.0	11690.0	26887.0	71255.9	...	16040.5	30342.0	10541.0	14960.0	1043.0	17898.8	6556.6	2011.0	2579.4	9306.9
2014	22926.0	10640.6	25208.9	12094.7	12158.2	20025.7	9966.5	12170.8	25269.8	64830.5	...	14623.8	28891.3	9173.1	14041.7	939.7	17402.5	6518.4	1847.7	2473.9	9264.5
2013	21134.6	9945.4	24259.6	11987.2	11392.4	19208.8	9427.9	11849.1	23204.1	59349.4	...	13027.6	26518.0	7973.1	12825.5	828.2	15905.4	6014.5	1713.3	2327.7	8392.6
2012	19024.7	9043.0	23077.5	11683.1	10470.1	17848.6	8678.0	11015.8	21305.6	53701.9	...	11595.4	23922.4	6742.2	11097.4	710.2	14142.4	5393.1	1528.5	2131.0	7411.8
2011	17188.8	8112.5	21384.7	10894.4	9458.1	16354.9	7734.6	9935.0	20009.7	48839.2	...	10161.2	21050.9	5615.6	9523.1	611.5	12175.1	4816.9	1370.4	1931.8	6532.0
2010	14964.0	6830.8	18003.6	8903.9	8199.9	13896.3	6410.5	8308.3	17915.4	41383.9	...	8065.3	17224.8	4519.0	7735.3	512.9	9845.2	3943.7	1144.2	1571.7	5360.2
2009	12900.9	5709.6	15306.9	7147.6	7104.2	12815.7	5434.8	7218.9	15742.4	34471.7	...	6651.2	14190.6	3856.7	6574.4	445.7	7997.8	3268.3	939.7	1266.7	4237.0
2008	11813.1	5182.4	14200.1	7223.0	6242.4	12137.7	4834.7	7134.2	14536.9	30945.5	...	5899.5	12756.2	3504.5	6016.6	398.2	7177.8	3071.7	896.9	1139.2	4142.5
2007	10425.5	4158.4	12152.9	5935.6	5166.9	10292.2	4080.3	6126.3	12878.7	25988.4	...	4770.7	10562.1	2847.5	5077.4	344.1	5681.8	2675.1	720.1	877.6	3500.0
2006	8387.0	3538.2	10043.0	4713.6	4161.8	8390.3	3226.5	5329.8	10598.9	21240.8	...	3900.3	8494.7	2264.1	4090.7	285.9	4595.6	2203.0	585.2	683.3	2957.3
2005	7149.8	3158.6	8773.4	4079.4	3523.7	7260.8	2776.5	4756.4	9197.1	18121.3	...	3448.4	7195.9	1939.9	3497.7	243.1	3817.2	1864.6	499.4	579.9	2520.5
2004	6252.5	2621.1	7588.6	3496.0	2942.4	6469.8	2455.2	4134.7	8101.6	14823.1	...	3059.5	6304.0	1649.4	3136.4	217.9	3141.6	1653.6	443.7	519.9	2170.4
2003	5267.2	2257.8	6333.6	2854.3	2388.4	5906.3	2141.0	3609.7	6804.0	12442.9	...	2615.6	5346.2	1429.0	2633.4	186.0	2587.7	1399.9	385.0	442.6	1889.2
2002	4525.7	1926.9	5518.9	2324.8	1940.9	5458.2	2043.1	3242.7	5795.0	10606.9	...	2279.8	4725.0	1243.4	2358.7	162.0	2253.4	1232.0	340.7	377.2	1612.6
2001	3861.5	1756.9	5062.9	2029.5	1713.8	5033.1	1900.9	3043.4	5257.7	9456.8	...	2014.6	4293.5	1133.3	2159.0	139.2	2010.6	1125.4	300.1	337.4	1491.6
2000	3277.8	1591.7	4628.2	1845.7	1539.1	4669.1	1751.4	2855.5	4812.2	8553.7	...	1822.1	3928.2	1029.9	2030.1	117.8	1804.0	1052.9	263.7	295.0	1363.6
1999	2759.8	1435.6	4158.9	1667.1	1379.3	4171.7	1673.0	2536.9	4222.3	7697.8	...	1687.8	3649.1	937.5	1899.8	106.0	1592.6	956.3	239.4	264.6	1163.2
1998	2439.1	1344.7	3924.5	1611.1	1262.5	3881.7	1577.1	2470.2	3831.0	7200.0	...	1622.4	3474.1	858.4	1831.3	91.5	1458.4	887.7	220.9	245.5	1107.0
1997	2118.1	1264.6	3652.1	1476.0	1153.5	3582.5	1464.3	2397.6	3465.3	6680.3	...	1525.3	3241.5	805.8	1676.2	77.2	1363.6	793.6	202.8	224.6	1039.8
1996	1819.4	1121.9	3198.0	1292.1	1023.1	3157.7	1346.8	2137.6	2980.8	6004.2	...	1326.4	2871.7	723.2	1517.7	65.0	1215.8	722.5	184.2	202.9	900.9
1995	1516.2	932.0	2701.2	1076.0	857.1	2793.4	1137.2	1790.2	2518.1	5155.3	...	1130.6	2443.2	636.2	1222.2	56.1	1036.9	557.8	167.8	175.2	814.9
1994	1149.8	732.9	2114.5	826.7	695.1	2461.8	937.7	1448.1	1990.9	4057.4	...	838.1	2001.4	524.5	983.8	46.0	839.0	453.6	138.4	136.3	662.3
1993	888.9	538.9	1620.8	680.4	537.8	2010.8	718.6	1075.3	1519.2	2998.2	...	611.1	1486.1	417.7	783.3	37.4	678.2	372.2	109.7	104.5	495.3
1992	710.2	411.0	1278.5	551.1	421.7	1473.0	558.1	857.4	1114.3	2136.0	...	462.5	1177.3	339.9	618.7	33.3	531.6	317.8	87.5	83.1	402.3

	2020	2019	2018	2017	2016	2015	2014	2013	2012	2011	...	2001	2000	1999	1998	1997	1996	1995	1994	1993	1992
北京市	36102.6	35445.1	33106.0	29883.0	27041.2	24779.1	22926.0	21134.6	19024.7	17188.8	...	3861.5	3277.8	2759.8	2439.1	2118.1	1819.4	1516.2	1149.8	888.9	710.2
天津市	14083.7	14055.5	13362.9	12450.6	11477.2	10879.5	10640.6	9945.4	9043.0	8112.5	...	1756.9	1591.7	1435.6	1344.7	1264.6	1121.9	932.0	732.9	538.9	411.0
河北省	36206.9	34978.6	32494.6	30640.8	28474.1	26398.4	25208.9	24259.6	23077.5	21384.7	...	5062.9	4628.2	4158.9	3924.5	3652.1	3198.0	2701.2	2114.5	1620.8	1278.5
山西省	17651.9	16961.6	15958.1	14484.3	11946.4	11836.4	12094.7	11987.2	11683.1	10894.4	...	2029.5	1845.7	1667.1	1611.1	1476.0	1292.1	1076.0	826.7	680.4	551.1
内蒙古自治区	17359.8	17212.5	16140.8	14898.1	13789.3	12949.0	12158.2	11392.4	10470.1	9458.1	...	1713.8	1539.1	1379.3	1262.5	1153.5	1023.1	857.1	695.1	537.8	421.7
辽宁省	25115.0	24855.3	23510.5	21693.0	20392.5	20210.3	20025.7	19208.8	17848.6	16354.9	...	5033.1	4669.1	4171.7	3881.7	3582.5	3157.7	2793.4	2461.8	2010.8	1473.0
吉林省	12311.3	11726.8	11253.8	10922.0	10427.0	10018.0	9966.5	9427.9	8678.0	7734.6	...	1900.9	1751.4	1673.0	1577.1	1464.3	1346.8	1137.2	937.7	718.6	558.1
黑龙江省	13698.5	13544.4	12846.5	12313.0	11895.0	11690.0	12170.8	11849.1	11015.8	9935.0	...	3043.4	2855.5	2536.9	2470.2	2397.6	2137.6	1790.2	1448.1	1075.3	857.4
上海市	38700.6	37987.6	36011.8	32925.0	29887.0	26887.0	25269.8	23204.1	21305.6	20009.7	...	5257.7	4812.2	4222.3	3831.0	3465.3	2980.8	2518.1	1990.9	1519.2	1114.3
江苏省	102719.0	98656.8	93207.6	85869.8	77350.9	71255.9	64830.5	59349.4	53701.9	48839.2	...	9456.8	8553.7	7697.8	7200.0	6680.3	6004.2	5155.3	4057.4	2998.2	2136.0
浙江省	64613.3	62462.0	58002.8	52403.1	47254.0	43507.7	40023.5	37334.6	34382.4	31854.8	...	6927.7	6164.8	5461.3	5065.5	4695.9	4195.8	3563.9	2689.3	1925.9	1375.7
安徽省	38680.6	36845.5	34010.9	29676.2	26307.7	23831.2	22519.7	20584.0	18341.7	16284.9	...	3502.8	3125.3	2907.8	2711.7	2485.4	2199.7	1891.2	1378.9	1073.5	827.0
福建省	43903.9	42326.6	38687.8	33842.4	29609.4	26819.5	24942.1	22503.8	20190.7	17917.7	...	4072.9	3764.5	3414.2	3159.9	2870.9	2484.3	2094.9	1644.4	1114.2	784.7
江西省	25691.5	24667.3	22716.5	20210.8	18388.6	16780.9	15667.8	14300.2	12807.7	11584.5	...	2175.7	2003.1	1853.7	1719.9	1605.8	1409.7	1169.7	948.2	723.0	572.6
山东省	73129.0	70540.5	66648.9	63012.1	58762.5	55288.8	50774.8	47344.3	42957.3	39064.9	...	9076.2	8278.1	7493.8	7021.4	6537.1	5883.8	4953.4	3844.5	2770.4	2196.5
河南省	54997.1	53717.8	49935.9	44824.9	40249.3	37084.1	34574.8	31632.5	28961.9	26318.7	...	5533.0	5053.0	4517.9	4308.2	4041.1	3634.7	2988.4	2216.8	1660.2	1279.8
湖北省	43443.5	45429.0	42022.0	37235.0	33353.0	30344.0	28242.1	25378.0	22590.9	19942.5	...	3880.5	3545.4	3229.3	3114.0	2856.5	2499.8	2109.4	1700.9	1325.8	1088.4
湖南省	41781.5	39894.1	36329.7	33828.1	30853.5	28538.6	25881.3	23545.2	21207.2	18915.0	...	3831.9	3551.5	3214.5	3025.5	2849.3	2540.1	2132.1	1650.0	1244.7	987.0
广东省	110760.9	107986.9	99945.2	91648.7	82163.2	74732.4	68173.0	62503.4	57007.7	53072.8	...	12126.6	10810.2	9289.6	8555.3	7793.0	6848.2	5940.3	4619.0	3469.3	2447.5
广西壮族自治区	22156.7	21237.1	19627.8	17790.7	16116.6	14797.8	13587.8	12448.4	11303.6	10299.9	...	2279.3	2080.0	1971.4	1911.3	1817.3	1697.9	1497.6	1198.3	871.7	646.6
海南省	5532.4	5330.8	4910.7	4497.5	4090.2	3734.2	3449.0	3115.9	2789.4	2463.8	...	579.2	526.8	476.7	442.1	411.2	389.7	363.3	332.0	260.4	184.9
重庆市	25002.8	23605.8	21588.8	20066.3	18023.0	16040.5	14623.8	13027.6	11595.4	10161.2	...	2014.6	1822.1	1687.8	1622.4	1525.3	1326.4	1130.6	838.1	611.1	462.5
四川省	48598.8	46363.8	42902.1	37905.1	33138.5	30342.0	28891.3	26518.0	23922.4	21050.9	...	4293.5	3928.2	3649.1	3474.1	3241.5	2871.7	2443.2	2001.4	1486.1	1177.3
贵州省	17826.6	16769.3	15353.2	13605.4	11792.4	10541.0	9173.1	7973.1	6742.2	5615.6	...	1133.3	1029.9	937.5	858.4	805.8	723.2	636.2	524.5	417.7	339.9
云南省	24521.9	23223.8	20880.6	18486.0	16369.0	14960.0	14041.7	12825.5	11097.4	9523.1	...	2159.0	2030.1	1899.8	1831.3	1676.2	1517.7	1222.2	983.8	783.3	618.7
西藏自治区	1902.7	1697.8	1548.4	1349.0	1173.0	1043.0	939.7	828.2	710.2	611.5	...	139.2	117.8	106.0	91.5	77.2	65.0	56.1	46.0	37.4	33.3
陕西省	26181.9	25793.2	23941.9	21473.5	19045.8	17898.8	17402.5	15905.4	14142.4	12175.1	...	2010.6	1804.0	1592.6	1458.4	1363.6	1215.8	1036.9	839.0	678.2	531.6
甘肃省	9016.7	8718.3	8104.1	7336.7	6907.9	6556.6	6518.4	6014.5	5393.1	4816.9	...	1125.4	1052.9	956.3	887.7	793.6	722.5	557.8	453.6	372.2	317.8
青海省	3005.9	2941.1	2748.0	2465.1	2258.2	2011.0	1847.7	1713.3	1528.5	1370.4	...	300.1	263.7	239.4	220.9	202.8	184.2	167.8	138.4	109.7	87.5
宁夏回族自治区	3920.6	3748.5	3510.2	3200.3	2781.4	2579.4	2473.9	2327.7	2131.0	1931.8	...	337.4	295.0	264.6	245.5	224.6	202.9	175.2	136.3	104.5	83.1
新疆维吾尔自治区	13797.6	13597.1	12809.4	11159.9	9630.8	9306.9	9264.5	8392.6	7411.8	6532.0	...	1491.6	1363.6	1163.2	1107.0	1039.8	900.9	814.9	662.3	495.3	402.3

	2020	2019	2018	2017	2016	2015	2014	2013	2012	2011	...	2001	2000	1999	1998	1997	1996	1995	1994	1993	1992
北京市	36102.6	35445.1	33106.0	29883.0	27041.2	24779.1	22926.0	21134.6	19024.7	17188.8	...	3861.5	3277.8	2759.8	2439.1	2118.1	1819.4	1516.2	1149.8	888.9	710.2
天津市	14083.7	14055.5	13362.9	12450.6	11477.2	10879.5	10640.6	9945.4	9043.0	8112.5	...	1756.9	1591.7	1435.6	1344.7	1264.6	1121.9	932.0	732.9	538.9	411.0
河北省	36206.9	34978.6	32494.6	30640.8	28474.1	26398.4	25208.9	24259.6	23077.5	21384.7	...	5062.9	4628.2	4158.9	3924.5	3652.1	3198.0	2701.2	2114.5	1620.8	1278.5
山西省	17651.9	16961.6	15958.1	14484.3	11946.4	11836.4	12094.7	11987.2	11683.1	10894.4	...	2029.5	1845.7	1667.1	1611.1	1476.0	1292.1	1076.0	826.7	680.4	551.1
内蒙古自治区	17359.8	17212.5	16140.8	14898.1	13789.3	12949.0	12158.2	11392.4	10470.1	9458.1	...	1713.8	1539.1	1379.3	1262.5	1153.5	1023.1	857.1	695.1	537.8	421.7
辽宁省	25115.0	24855.3	23510.5	21693.0	20392.5	20210.3	20025.7	19208.8	17848.6	16354.9	...	5033.1	4669.1	4171.7	3881.7	3582.5	3157.7	2793.4	2461.8	2010.8	1473.0
吉林省	12311.3	11726.8	11253.8	10922.0	10427.0	10018.0	9966.5	9427.9	8678.0	7734.6	...	1900.9	1751.4	1673.0	1577.1	1464.3	1346.8	1137.2	937.7	718.6	558.1
黑龙江省	13698.5	13544.4	12846.5	12313.0	11895.0	11690.0	12170.8	11849.1	11015.8	9935.0	...	3043.4	2855.5	2536.9	2470.2	2397.6	2137.6	1790.2	1448.1	1075.3	857.4
上海市	38700.6	37987.6	36011.8	32925.0	29887.0	26887.0	25269.8	23204.1	21305.6	20009.7	...	5257.7	4812.2	4222.3	3831.0	3465.3	2980.8	2518.1	1990.9	1519.2	1114.3
江苏省	102719.0	98656.8	93207.6	85869.8	77350.9	71255.9	64830.5	59349.4	53701.9	48839.2	...	9456.8	8553.7	7697.8	7200.0	6680.3	6004.2	5155.3	4057.4	2998.2	2136.0
浙江省	64613.3	62462.0	58002.8	52403.1	47254.0	43507.7	40023.5	37334.6	34382.4	31854.8	...	6927.7	6164.8	5461.3	5065.5	4695.9	4195.8	3563.9	2689.3	1925.9	1375.7
安徽省	38680.6	36845.5	34010.9	29676.2	26307.7	23831.2	22519.7	20584.0	18341.7	16284.9	...	3502.8	3125.3	2907.8	2711.7	2485.4	2199.7	1891.2	1378.9	1073.5	827.0
福建省	43903.9	42326.6	38687.8	33842.4	29609.4	26819.5	24942.1	22503.8	20190.7	17917.7	...	4072.9	3764.5	3414.2	3159.9	2870.9	2484.3	2094.9	1644.4	1114.2	784.7
江西省	25691.5	24667.3	22716.5	20210.8	18388.6	16780.9	15667.8	14300.2	12807.7	11584.5	...	2175.7	2003.1	1853.7	1719.9	1605.8	1409.7	1169.7	948.2	723.0	572.6
山东省	73129.0	70540.5	66648.9	63012.1	58762.5	55288.8	50774.8	47344.3	42957.3	39064.9	...	9076.2	8278.1	7493.8	7021.4	6537.1	5883.8	4953.4	3844.5	2770.4	2196.5
河南省	54997.1	53717.8	49935.9	44824.9	40249.3	37084.1	34574.8	31632.5	28961.9	26318.7	...	5533.0	5053.0	4517.9	4308.2	4041.1	3634.7	2988.4	2216.8	1660.2	1279.8
湖北省	43443.5	45429.0	42022.0	37235.0	33353.0	30344.0	28242.1	25378.0	22590.9	19942.5	...	3880.5	3545.4	3229.3	3114.0	2856.5	2499.8	2109.4	1700.9	1325.8	1088.4
湖南省	41781.5	39894.1	36329.7	33828.1	30853.5	28538.6	25881.3	23545.2	21207.2	18915.0	...	3831.9	3551.5	3214.5	3025.5	2849.3	2540.1	2132.1	1650.0	1244.7	987.0
广东省	110760.9	107986.9	99945.2	91648.7	82163.2	74732.4	68173.0	62503.4	57007.7	53072.8	...	12126.6	10810.2	9289.6	8555.3	7793.0	6848.2	5940.3	4619.0	3469.3	2447.5
广西壮族自治区	22156.7	21237.1	19627.8	17790.7	16116.6	14797.8	13587.8	12448.4	11303.6	10299.9	...	2279.3	2080.0	1971.4	1911.3	1817.3	1697.9	1497.6	1198.3	871.7	646.6
海南省	5532.4	5330.8	4910.7	4497.5	4090.2	3734.2	3449.0	3115.9	2789.4	2463.8	...	579.2	526.8	476.7	442.1	411.2	389.7	363.3	332.0	260.4	184.9
重庆市	25002.8	23605.8	21588.8	20066.3	18023.0	16040.5	14623.8	13027.6	11595.4	10161.2	...	2014.6	1822.1	1687.8	1622.4	1525.3	1326.4	1130.6	838.1	611.1	462.5
四川省	48598.8	46363.8	42902.1	37905.1	33138.5	30342.0	28891.3	26518.0	23922.4	21050.9	...	4293.5	3928.2	3649.1	3474.1	3241.5	2871.7	2443.2	2001.4	1486.1	1177.3
贵州省	17826.6	16769.3	15353.2	13605.4	11792.4	10541.0	9173.1	7973.1	6742.2	5615.6	...	1133.3	1029.9	937.5	858.4	805.8	723.2	636.2	524.5	417.7	339.9
云南省	24521.9	23223.8	20880.6	18486.0	16369.0	14960.0	14041.7	12825.5	11097.4	9523.1	...	2159.0	2030.1	1899.8	1831.3	1676.2	1517.7	1222.2	983.8	783.3	618.7
西藏自治区	1902.7	1697.8	1548.4	1349.0	1173.0	1043.0	939.7	828.2	710.2	611.5	...	139.2	117.8	106.0	91.5	77.2	65.0	56.1	46.0	37.4	33.3
陕西省	26181.9	25793.2	23941.9	21473.5	19045.8	17898.8	17402.5	15905.4	14142.4	12175.1	...	2010.6	1804.0	1592.6	1458.4	1363.6	1215.8	1036.9	839.0	678.2	531.6
甘肃省	9016.7	8718.3	8104.1	7336.7	6907.9	6556.6	6518.4	6014.5	5393.1	4816.9	...	1125.4	1052.9	956.3	887.7	793.6	722.5	557.8	453.6	372.2	317.8
青海省	3005.9	2941.1	2748.0	2465.1	2258.2	2011.0	1847.7	1713.3	1528.5	1370.4	...	300.1	263.7	239.4	220.9	202.8	184.2	167.8	138.4	109.7	87.5
宁夏回族自治区	3920.6	3748.5	3510.2	3200.3	2781.4	2579.4	2473.9	2327.7	2131.0	1931.8	...	337.4	295.0	264.6	245.5	224.6	202.9	175.2	136.3	104.5	83.1
新疆维吾尔自治区	13797.6	13597.1	12809.4	11159.9	9630.8	9306.9	9264.5	8392.6	7411.8	6532.0	...	1491.6	1363.6	1163.2	1107.0	1039.8	900.9	814.9	662.3	495.3	402.3

	价格	小区	房屋户型	建筑面积	户型结构	建筑类型	房屋朝向	建筑结构	装修情况	梯户比例	...	环	室	厅	厨	卫	所处楼层	总层数	有无抵押	抵押情况	均价
0	1410.0	江临天下	4室2厅1厨2卫	165.73	平层	板楼	南西南	钢混结构	精装	六梯六户	...	内环内	4	2	1	2	低楼层	35	无	NaN	85078.14
1	680.0	樱花路309弄	2室2厅1厨1卫	78.65	复式	板楼	南北	钢混结构	精装	一梯两户	...	内环内	2	2	1	1	高楼层	6	有	150万元银行抵押业主自还	86459.00
2	2088.0	盛大金磐	3室2厅1厨3卫	194.65	平层	板楼	南	钢混结构	精装	三梯三户	...	内环内	3	2	1	3	中楼层	43	无	NaN	107269.46
3	266.0	康桥月苑	2室2厅1厨1卫	72.27	平层	板楼	南	钢混结构	精装	一梯两户	...	外环外	2	2	1	1	高楼层	6	无	NaN	36806.42
4	2288.0	城市经典	4室2厅1厨3卫	324.29	暂无数据	暂无数据	北	钢混结构	精装	暂无数据	...	内环至中环	4	2	1	3	中楼层	4	无	NaN	70554.13
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
37478	260.0	绿地金卫新家园	4室2厅1厨2卫	154.74	复式	板楼	南	钢混结构	精装	一梯两户	...	外环外	4	2	1	2	高楼层	6	有	30万元公积金	16802.38
37479	135.0	城西花苑	2室2厅1厨1卫	94.00	平层	板楼	南	钢混结构	毛坯	一梯两户	...	外环外	2	2	1	1	中楼层	6	无	NaN	14361.70
37480	135.0	东礁四村	3室1厅1厨1卫	73.00	平层	板楼	南	钢混结构	简装	一梯三户	...	外环外	3	1	1	1	高楼层	6	有	20万元业主自还	18493.15
37481	320.0	万盛金邸	4室1厅1厨2卫	128.56	平层	板楼	南	钢混结构	精装	一梯两户	...	外环外	4	1	1	2	低楼层	14	有	8万元业主自还	24891.10
37482	208.0	育秀六区	3室1厅1厨1卫	88.00	平层	板楼	南	砖混结构	精装	一梯两户	...	NaN	3	1	1	1	中楼层	5	无	NaN	23636.36

	价格	均价
区
嘉定区	298.100956	3.346117
奉贤区	244.201167	2.349471
宝山区	392.535022	4.403582
徐汇区	661.666783	7.670740
普陀区	522.432921	6.090767
杨浦区	478.377571	6.364288
松江区	517.619973	3.798396
浦东新区	573.529333	5.670892
虹口区	570.579395	6.647432
金山区	206.206807	2.029167
长宁区	733.222088	7.141097
闵行区	521.933185	5.112870
青浦区	685.365884	3.667959
静安区	698.138963	7.651275
黄浦区	1255.955154	9.825114

	sepal_length	sepal_width	petal_length	petal_width	species
0	5.1	3.5	1.4	0.2	setosa
1	4.9	3.0	1.4	0.2	setosa
2	4.7	3.2	1.3	0.2	setosa
3	4.6	3.1	1.5	0.2	setosa
4	5.0	3.6	1.4	0.2	setosa
...	...	...	...	...	...
145	6.7	3.0	5.2	2.3	virginica
146	6.3	2.5	5.0	1.9	virginica
147	6.5	3.0	5.2	2.0	virginica
148	6.2	3.4	5.4	2.3	virginica
149	5.9	3.0	5.1	1.8	virginica