Mastery Day 2.ipynb

Kernel: Python 3 (system-wide)

Library Imports Here

#import pandas here
import pandas as pd

#import numpy here
import numpy as np

#import sklearn
import sklearn

#import matplot
import matplotlib.pyplot as plt

#import kmeans
from sklearn.cluster import KMeans

Data Frame Reading and Practice

#read in your SAT data
sat_data = pd.read_csv("2012_SAT_Results.csv")

#print the first five rows using head()
sat_data.head()

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
0	01M292	HENRY STREET SCHOOL FOR INTERNATIONAL STUDIES	29	355	404	363
1	01M448	UNIVERSITY NEIGHBORHOOD HIGH SCHOOL	91	383	423	366
2	01M450	EAST SIDE COMMUNITY SCHOOL	70	377	402	370
3	01M458	FORSYTH SATELLITE ACADEMY	7	414	401	359
4	01M509	MARTA VALLE HIGH SCHOOL	44	390	433	384

#print the last five rows using tail
sat_data.tail()

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
473	75X012	P.S. X012 LEWIS AND CLARK SCHOOL	s	s	s	s
474	75X754	J. M. RAPPORT SCHOOL CAREER DEVELOPMENT	s	s	s	s
475	79M645	SCHOOL FOR COOPERATIVE TECHNICAL EDUCATION	s	s	s	s
476	79Q950	GED PLUS s CITYWIDE	8	496	400	426
477	79X490	PHOENIX ACADEMY	9	367	370	360

#find out how many colums and rows our data is
sat_data.shape

(478, 6)

#print the columns
sat_data.columns

Index(['DBN', 'SCHOOL NAME', 'Num of SAT Test Takers',
       'SAT Critical Reading Avg. Score', 'SAT Math Avg. Score',
       'SAT Writing Avg. Score'],
      dtype='object')

#print the types of data 

#describe the data

#slice 15 rows of your the data 

#slice 15 rows of a column

#slice 15 rows of two columns of data together

#slices 15 rows of three columns of data together

#slices the last 10 rows of three columns of data together

#Find the values of a column of data
sat_data["SCHOOL NAME"].value_counts()

WASHINGTON IRVING YABC                                                            1
HILLCREST HIGH SCHOOL                                                             1
LEON M. GOLDSTEIN HIGH SCHOOL FOR THE SCIENCES                                    1
HIGH SCHOOL FOR HEALTH PROFESSIONS AND HUMAN SERVICES                             1
ART AND DESIGN HIGH SCHOOL                                                        1
                                                                                 ..
BRONX CAREER AND COLLEGE PREPARATORY HIGH SCHOOL                                  1
ACADEMY FOR COLLEGE PREPARATION AND CAREER EXPLORATION: A COLLEGE BOARD SCHOOL    1
BENJAMIN BANNEKER ACADEMY                                                         1
PERFORMING ARTS AND TECHNOLOGY HIGH SCHOOL                                        1
JOHN ADAMS HIGH SCHOOL                                                            1
Name: SCHOOL NAME, Length: 478, dtype: int64

#count the number of eaxh type of value for a column of data

#use conditional formatting to render a part of your data and store it as a variable

#Use 2 conditional formats to render a part of your data and store it as a variable

#count the value types of your stored variables separately

Image Processing

import os

from IPython.display import Image

Image(filename = "machinelearning.png", height = 1000, width = 1000)

Image(filename = "unsupervised.png", height = 1000, width = 1000)

Image(filename = "kmeansalg.png", height = 1000, width = 1000)

Data PreProcessing and Cleaning

sat_data.head()

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
0	01M292	HENRY STREET SCHOOL FOR INTERNATIONAL STUDIES	29	355	404	363
1	01M448	UNIVERSITY NEIGHBORHOOD HIGH SCHOOL	91	383	423	366
2	01M450	EAST SIDE COMMUNITY SCHOOL	70	377	402	370
3	01M458	FORSYTH SATELLITE ACADEMY	7	414	401	359
4	01M509	MARTA VALLE HIGH SCHOOL	44	390	433	384

sat_data.drop("DBN", axis = 1,  inplace=True)

sat_data.head()

	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
0	HENRY STREET SCHOOL FOR INTERNATIONAL STUDIES	29	355	404	363
1	UNIVERSITY NEIGHBORHOOD HIGH SCHOOL	91	383	423	366
2	EAST SIDE COMMUNITY SCHOOL	70	377	402	370
3	FORSYTH SATELLITE ACADEMY	7	414	401	359
4	MARTA VALLE HIGH SCHOOL	44	390	433	384

sat_data.columns

Index(['SCHOOL NAME', 'Num of SAT Test Takers',
       'SAT Critical Reading Avg. Score', 'SAT Math Avg. Score',
       'SAT Writing Avg. Score'],
      dtype='object')

import seaborn as sns

col_list = ['Num of SAT Test Takers','SAT Critical Reading Avg. Score', 'SAT Math Avg. Score', 'SAT Writing Avg. Score']

for col in col_list:
    sns.countplot(x = col, data = sat_data, palette = 'Set3')# hue = 'Good Loan')
    plt.xticks(rotation=90)
    plt.show()

sat_data.isnull().sum()
#isnull returns a boolean value of True or False depending on whether there is an empty cell in our data set
#we can use .sum() to count it. 

SCHOOL NAME                        0
Num of SAT Test Takers             0
SAT Critical Reading Avg. Score    0
SAT Math Avg. Score                0
SAT Writing Avg. Score             0
dtype: int64

sat_data["Num of SAT Test Takers"].unique()
#unique tells us values in a column of data that is special or has little to one occurence 

array(['29', '91', '70', '7', '44', '112', '159', '18', '130', '16', '62',
       '53', '58', '85', '48', '76', '50', '40', '69', '42', '60', '92',
       's', '79', '263', '54', '94', '104', '114', '66', '103', '127',
       '144', '336', '84', '95', '59', '72', '49', '151', '832', '167',
       '25', '81', '264', '131', '73', '14', '78', '26', '77', '56', '30',
       '33', '121', '9', '335', '36', '83', '154', '191', '270', '61',
       '27', '41', '12', '32', '261', '531', '75', '35', '111', '43',
       '375', '51', '31', '20', '214', '101', '55', '63', '24', '228',
       '65', '34', '64', '28', '47', '52', '67', '39', '415', '6', '68',
       '80', '74', '38', '113', '86', '57', '443', '731', '109', '99',
       '10', '46', '97', '189', '37', '1277', '90', '105', '8', '13',
       '89', '185', '102', '134', '142', '141', '71', '165', '259', '17',
       '182', '456', '238', '694', '385', '475', '727', '448', '119',
       '824', '518', '236', '11', '155', '320', '241', '138', '396', '45',
       '558', '347', '278', '888', '934', '334', '708', '175', '87', '93',
       '404', '403', '194', '762', '462', '422', '98', '395', '392',
       '174', '148', '143', '135', '137', '107', '391', '271', '807',
       '535', '227', '88', '23'], dtype=object)

sat_data.columns

Index(['SCHOOL NAME', 'Num of SAT Test Takers',
       'SAT Critical Reading Avg. Score', 'SAT Math Avg. Score',
       'SAT Writing Avg. Score'],
      dtype='object')

sat_data['SAT Critical Reading Avg. Score'].unique()

array(['355', '383', '377', '414', '390', '332', '522', '417', '624',
       '395', '409', '394', '374', '423', '404', '353', '375', '403',
       '408', '373', '391', '473', 's', '319', '465', '492', '509', '496',
       '537', '517', '468', '572', '528', '429', '416', '356', '441',
       '378', '376', '679', '443', '370', '469', '407', '336', '389',
       '412', '368', '405', '498', '527', '350', '345', '458', '426',
       '399', '444', '406', '384', '371', '577', '566', '396', '433',
       '401', '354', '461', '432', '369', '358', '357', '413', '360',
       '605', '362', '380', '365', '363', '400', '430', '339', '364',
       '379', '310', '361', '351', '420', '367', '387', '398', '337',
       '402', '366', '324', '372', '411', '393', '459', '386', '382',
       '315', '314', '438', '304', '300', '392', '343', '419', '632',
       '348', '636', '381', '431', '388', '347', '321', '342', '352',
       '439', '587', '305', '435', '471', '586', '397', '359', '287',
       '338', '457', '418', '385', '476', '425', '313', '410', '341',
       '279', '326', '478', '436', '524', '456', '349', '311', '317',
       '545', '445', '455', '621', '480', '462', '499', '452', '513',
       '612', '504', '323', '487', '472', '424', '437', '466', '635',
       '428'], dtype=object)

sat_data['SAT Math Avg. Score'].unique()

array(['404', '423', '402', '401', '433', '557', '574', '418', '604',
       '400', '393', '384', '375', '438', '449', '358', '388', '392',
       '390', '370', '391', '483', 's', '512', '493', '465', '490', '563',
       '590', '533', '492', '594', '553', '399', '426', '357', '473',
       '365', '416', '460', '387', '735', '489', '349', '472', '440',
       '425', '378', '395', '371', '581', '436', '508', '337', '517',
       '403', '379', '382', '441', '424', '368', '575', '564', '398',
       '369', '506', '514', '421', '446', '351', '318', '366', '353',
       '360', '474', '361', '654', '376', '380', '422', '456', '364',
       '324', '359', '394', '396', '356', '411', '381', '386', '385',
       '373', '355', '464', '367', '480', '363', '339', '312', '419',
       '315', '455', '412', '406', '333', '408', '350', '420', '688',
       '362', '435', '648', '471', '397', '372', '344', '432', '323',
       '346', '374', '417', '659', '383', '443', '499', '584', '410',
       '377', '335', '415', '341', '342', '462', '481', '413', '320',
       '322', '478', '486', '477', '427', '437', '496', '468', '414',
       '519', '475', '561', '409', '338', '454', '429', '568', '447',
       '498', '463', '451', '651', '458', '545', '539', '523', '434',
       '537', '491', '445', '452', '497', '660', '488', '682', '317',
       '444'], dtype=object)

sat_data['SAT Writing Avg. Score'].unique()

array(['363', '366', '370', '359', '384', '316', '525', '411', '628',
       '387', '392', '378', '362', '432', '416', '340', '385', '405',
       '390', '394', '479', 's', '357', '461', '467', '523', '518', '550',
       '515', '459', '592', '533', '381', '428', '391', '349', '458',
       '368', '388', '360', '682', '442', '351', '475', '393', '400',
       '420', '344', '382', '335', '431', '352', '477', '512', '345',
       '343', '403', '429', '426', '376', '430', '408', '374', '358',
       '577', '402', '361', '373', '455', '395', '448', '333', '398',
       '342', '364', '404', '355', '588', '367', '399', '346', '423',
       '326', '348', '311', '371', '383', '407', '389', '375', '350',
       '413', '365', '356', '377', '415', '457', '297', '339', '379',
       '369', '440', '302', '301', '330', '372', '410', '427', '649',
       '414', '354', '317', '636', '433', '353', '419', '341', '298',
       '312', '418', '587', '570', '396', '380', '300', '425', '334',
       '291', '441', '386', '286', '424', '314', '435', '476', '439',
       '542', '331', '332', '421', '329', '406', '443', '318', '481',
       '638', '489', '464', '401', '496', '454', '502', '596', '412',
       '494', '491', '544', '450', '466', '417', '470', '397', '422'],
      dtype=object)

#prints out the rows of data that have an s entry in the SAT Crit Reading column
sat_data[sat_data['SAT Critical Reading Avg. Score'] == "s"]

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
22	02M392	MANHATTAN BUSINESS ACADEMY	s	s	s	s
23	02M393	BUSINESS OF SPORTS SCHOOL	s	s	s	s
25	02M399	THE HIGH SCHOOL FOR LANGUAGE AND DIPLOMACY	s	s	s	s
38	02M427	MANHATTAN ACADEMY FOR ARTS & LANGUAGE	s	s	s	s
40	02M437	HUDSON HIGH SCHOOL OF LEARNING TECHNOLOGIES	s	s	s	s
41	02M438	INTERNATIONAL HIGH SCHOOL AT UNION SQUARE	s	s	s	s
47	02M473	WASHINGTON IRVING YABC	s	s	s	s
77	03M402	THE URBAN ASSEMBLY SCHOOL FOR GREEN CAREERS	s	s	s	s
78	03M403	THE GLOBAL LEARNING COLLABORATIVE	s	s	s	s
81	03M417	FRANK MCCOURT HIGH SCHOOL	s	s	s	s
89	03M577	YOUNG ADULT BOROUGH CENTER AT LOUIS D. BRANDEI...	s	s	s	s
100	05M362	COLUMBIA SECONDARY SCHOOL FOR MATH, SCIENCE, A...	s	s	s	s
111	06M423	HIGH SCHOOL FOR EXCELLENCE AND INNOVATION	s	s	s	s
122	07X379	JILL CHAIFETZ TRANSFER HIGH SCHOOL	s	s	s	s
123	07X381	BRONX HAVEN HIGH SCHOOL	s	s	s	s
136	08X269	BRONX STUDIO SCHOOL FOR WRITERS AND ARTISTS	s	s	s	s
143	08X367	ARCHIMEDES ACADEMY FOR MATH, SCIENCE AND TECHN...	s	s	s	s
144	08X376	ANTONIA PANTOJA PREPARATORY ACADEMY, A COLLEGE...	s	s	s	s
148	08X432	BRONX BRIDGES HIGH SCHOOL	s	s	s	s
150	08X507	STEVENSON YABC	s	s	s	s
153	08X537	BRONX ARENA HIGH SCHOOL	s	s	s	s
167	09X324	BRONX EARLY COLLEGE ACADEMY FOR TEACHING & LEA...	s	s	s	s
186	10X319	PROVIDING URBAN LEARNERS SUCCESS IN EDUCATION ...	s	s	s	s
201	10X478	LEARNING TO WORK GED AT JOHN F. KENNEDY	s	s	s	s
216	11X417	YOUNG ADULT BOROUGH CNTR CHRISTOPHER COLUMBUS HS	s	s	s	s
219	11X456	LEARNING TO WORK YABC AT TRUMAN HIGH SCHOOL	s	s	s	s
234	12X428	LEARNING TO WORK YABC AT MONROE ACADEMY	s	s	s	s
236	12X478	THE CINEMA SCHOOL	s	s	s	s
237	12X479	BRONX CAREER AND COLLEGE PREPARATORY HIGH SCHOOL	s	s	s	s
254	13K527	URBAN ASSEMBLY INSTITUTE OF MATH AND SCIENCE F...	s	s	s	s
259	13K616	BROOKLYN HIGH SCHOOL FOR LEADERSHIP AND COMMUN...	s	s	s	s
263	14K322	FOUNDATIONS ACADEMY	s	s	s	s
277	14K923	AUTOMOTIVE HIGH SCHOOL YABC	s	s	s	s
286	15K529	WEST BROOKLYN COMMUNITY HIGH SCHOOL	s	s	s	s
289	15K667	SUNSET PARK HIGH SCHOOL	s	s	s	s
295	16K688	THE BROOKLYN ACADEMY OF GLOBAL FINANCE	s	s	s	s
298	17K467	ERASMUS YABC	s	s	s	s
315	17K751	ACADEMY FOR HEALTH CAREERS	s	s	s	s
331	19K420	FRANKLIN K. LANE HIGH SCHOOL	s	s	s	s
332	19K431	THOMAS JEFFERSON YABC	s	s	s	s
348	20K609	THE URBAN ASSEMBLY SCHOOL FOR CRIMINAL JUSTICE	s	s	s	s
354	21K412/21K411	ABRAHAM LINCOLN YABC/LEARNING TO WORK GED AT A...	s	s	s	s
355	21K468	KINGSBOROUGH EARLY COLLEGE SCHOOL	s	s	s	s
380	24Q457	YOUNG ADULT BOROUGH CENTER AT ARTS AND BUSINES...	s	s	s	s
388	24Q744	VOYAGES PREPARATORY	s	s	s	s
416	28Q284	YORK EARLY COLLEGE ACADEMY	s	s	s	s
418	28Q325	HILLSIDE ARTS & LETTERS ACADEMY	s	s	s	s
426	28Q686	QUEENS METROPOLITAN HIGH SCHOOL	s	s	s	s
435	29Q326	CAMBRIA HEIGHTS ACADEMY	s	s	s	s
440	30Q286	YOUNG WOMEN'S LEADERSHIP SCHOOL, ASTORIA	s	s	s	s
468	75K371	P.S. 371 s LILLIAN L. RASHKIS	s	s	s	s
469	75M035	P.S. 035	s	s	s	s
470	75Q256	P.S. Q256	s	s	s	s
472	75R025	SOUTH RICHMOND HIGH SCHOOL I.S./P.S. 25	s	s	s	s
473	75X012	P.S. X012 LEWIS AND CLARK SCHOOL	s	s	s	s
474	75X754	J. M. RAPPORT SCHOOL CAREER DEVELOPMENT	s	s	s	s
475	79M645	SCHOOL FOR COOPERATIVE TECHNICAL EDUCATION	s	s	s	s

#Approach 1: Creating a function then using apply
def replace_s(row):
    if row == "s":
        return 300
    else:
        return row

#Then overwrite current column of the data set
sat_data['SAT Writing Avg. Score'] = sat_data['SAT Writing Avg. Score'].apply(replace_s)

sat_data['SAT Math Avg. Score'] = sat_data['SAT Math Avg. Score'].apply(replace_s)

sat_data['SAT Critical Reading Avg. Score'] = sat_data['SAT Critical Reading Avg. Score'].apply(replace_s)

#Check to see 
sat_data['SAT Writing Avg. Score'].dtypes

dtype('O')

#Condtionally checks for a specific entry in a specific column
sat_data[sat_data['SAT Critical Reading Avg. Score'] == "s"]

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score

def replace_with_zero(row):
    if row == "s":
        return 0
    else:
        return row

sat_data["Num of SAT Test Takers"] = sat_data["Num of SAT Test Takers"].apply(replace_with_zero)

#Condtionally checks for a specific entry in a specific column
sat_data[sat_data['Num of SAT Test Takers'] == "s"]

	DBN	SCHOOL NAME	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score

#only want numeric data
just_the_scores = sat_data[['Num of SAT Test Takers','SAT Critical Reading Avg. Score', 'SAT Math Avg. Score', 'SAT Writing Avg. Score']]

just_the_scores.head()

	Num of SAT Test Takers	SAT Critical Reading Avg. Score	SAT Math Avg. Score	SAT Writing Avg. Score
0	29	355	404	363
1	91	383	423	366
2	70	377	402	370
3	7	414	401	359
4	44	390	433	384

just_the_scores.dtypes

Num of SAT Test Takers             object
SAT Critical Reading Avg. Score    object
SAT Math Avg. Score                object
SAT Writing Avg. Score             object
dtype: object

just_the_scores["Num of SAT Test Takers"].unique()

array(['29', '91', '70', '7', '44', '112', '159', '18', '130', '16', '62',
       '53', '58', '85', '48', '76', '50', '40', '69', '42', '60', '92',
       0, '79', '263', '54', '94', '104', '114', '66', '103', '127',
       '144', '336', '84', '95', '59', '72', '49', '151', '832', '167',
       '25', '81', '264', '131', '73', '14', '78', '26', '77', '56', '30',
       '33', '121', '9', '335', '36', '83', '154', '191', '270', '61',
       '27', '41', '12', '32', '261', '531', '75', '35', '111', '43',
       '375', '51', '31', '20', '214', '101', '55', '63', '24', '228',
       '65', '34', '64', '28', '47', '52', '67', '39', '415', '6', '68',
       '80', '74', '38', '113', '86', '57', '443', '731', '109', '99',
       '10', '46', '97', '189', '37', '1277', '90', '105', '8', '13',
       '89', '185', '102', '134', '142', '141', '71', '165', '259', '17',
       '182', '456', '238', '694', '385', '475', '727', '448', '119',
       '824', '518', '236', '11', '155', '320', '241', '138', '396', '45',
       '558', '347', '278', '888', '934', '334', '708', '175', '87', '93',
       '404', '403', '194', '762', '462', '422', '98', '395', '392',
       '174', '148', '143', '135', '137', '107', '391', '271', '807',
       '535', '227', '88', '23'], dtype=object)

just_the_scores["Num of SAT Test Takers"].astype(int)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-34-eef83cd6674b> in <module>
----> 1 just_the_scores["Num of SAT Test Takers"].astype(int)

/usr/local/lib/python3.8/dist-packages/pandas/core/generic.py in astype(self, dtype, copy, errors)
   5541         else:
   5542             # else, only a single dtype is given
-> 5543             new_data = self._mgr.astype(dtype=dtype, copy=copy, errors=errors,)
   5544             return self._constructor(new_data).__finalize__(self, method="astype")
   5545 
/usr/local/lib/python3.8/dist-packages/pandas/core/internals/managers.py in astype(self, dtype, copy, errors)
    593         self, dtype, copy: bool = False, errors: str = "raise"
    594     ) -> "BlockManager":
--> 595         return self.apply("astype", dtype=dtype, copy=copy, errors=errors)
    596 
    597     def convert(
/usr/local/lib/python3.8/dist-packages/pandas/core/internals/managers.py in apply(self, f, align_keys, **kwargs)
    404                 applied = b.apply(f, **kwargs)
    405             else:
--> 406                 applied = getattr(b, f)(**kwargs)
    407             result_blocks = _extend_blocks(applied, result_blocks)
    408 
/usr/local/lib/python3.8/dist-packages/pandas/core/internals/blocks.py in astype(self, dtype, copy, errors)
    592             vals1d = values.ravel()
    593             try:
--> 594                 values = astype_nansafe(vals1d, dtype, copy=True)
    595             except (ValueError, TypeError):
    596                 # e.g. astype_nansafe can fail on object-dtype of strings
/usr/local/lib/python3.8/dist-packages/pandas/core/dtypes/cast.py in astype_nansafe(arr, dtype, copy, skipna)
    965         # work around NumPy brokenness, #1987
    966         if np.issubdtype(dtype.type, np.integer):
--> 967             return lib.astype_intsafe(arr.ravel(), dtype).reshape(arr.shape)
    968 
    969         # if we have a datetime/timedelta array of objects
pandas/_libs/lib.pyx in pandas._libs.lib.astype_intsafe()
ValueError: invalid literal for int() with base 10: 's'

#Fit the data
X_train = just_the_scores.values

kmeans = KMeans(n_clusters = 5, random_state = 100)
kmeans = kmeans.fit(X_train)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-26-d4efc6e7ac9c> in <module>
      1 kmeans = KMeans(n_clusters = 5, random_state = 100)
----> 2 kmeans = kmeans.fit(X_train)

/usr/local/lib/python3.8/dist-packages/sklearn/cluster/_kmeans.py in fit(self, X, y, sample_weight)
   1028             Fitted estimator.
   1029         """
-> 1030         X = self._validate_data(X, accept_sparse='csr',
   1031                                 dtype=[np.float64, np.float32],
   1032                                 order='C', copy=self.copy_x,
/usr/local/lib/python3.8/dist-packages/sklearn/base.py in _validate_data(self, X, y, reset, validate_separately, **check_params)
    418                     f"requires y to be passed, but the target y is None."
    419                 )
--> 420             X = check_array(X, **check_params)
    421             out = X
    422         else:
/usr/local/lib/python3.8/dist-packages/sklearn/utils/validation.py in inner_f(*args, **kwargs)
     70                           FutureWarning)
     71         kwargs.update({k: arg for k, arg in zip(sig.parameters, args)})
---> 72         return f(**kwargs)
     73     return inner_f
     74 
/usr/local/lib/python3.8/dist-packages/sklearn/utils/validation.py in check_array(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator)
    596                     array = array.astype(dtype, casting="unsafe", copy=False)
    597                 else:
--> 598                     array = np.asarray(array, order=order, dtype=dtype)
    599             except ComplexWarning:
    600                 raise ValueError("Complex data not supported\n"
/usr/local/lib/python3.8/dist-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 
ValueError: could not convert string to float: 's'