Created
November 2, 2019 08:16
-
-
Save Jeet1994/762d8429d02dc864c85d1b5d913cdff8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 97, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import pandas as pd" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 98, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train = pd.read_csv(\"train.csv\") " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 99, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test = pd.read_csv(\"test.csv\") " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 100, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"#used for splitting dataset if not already split, \n", | |
"from sklearn.model_selection import train_test_split\n", | |
"#x = data.iloc[:, :-1].values\n", | |
"#y = data.iloc[:, 1].values\n", | |
"#x_train, x_test, y_train, y_test = train_test_split(x, y,test_size=1/3, random_state=0)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 101, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"Loan_ID 0\n", | |
"Gender 13\n", | |
"Married 3\n", | |
"Dependents 15\n", | |
"Education 0\n", | |
"Self_Employed 32\n", | |
"ApplicantIncome 0\n", | |
"CoapplicantIncome 0\n", | |
"LoanAmount 22\n", | |
"Loan_Amount_Term 14\n", | |
"Credit_History 50\n", | |
"Property_Area 0\n", | |
"Loan_Status 0\n", | |
"dtype: int64" | |
] | |
}, | |
"execution_count": 101, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"train.apply(lambda x: sum(x.isnull()),axis=0) # checking missing values in each column of train dataset" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 102, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"Loan_ID 0\n", | |
"Gender 11\n", | |
"Married 0\n", | |
"Dependents 10\n", | |
"Education 0\n", | |
"Self_Employed 23\n", | |
"ApplicantIncome 0\n", | |
"CoapplicantIncome 0\n", | |
"LoanAmount 5\n", | |
"Loan_Amount_Term 6\n", | |
"Credit_History 29\n", | |
"Property_Area 0\n", | |
"dtype: int64" | |
] | |
}, | |
"execution_count": 102, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"test.apply(lambda x: sum(x.isnull()),axis=0) #checking missing values in each column of test dataset" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 103, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Gender = train.Gender.fillna('Male')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 104, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Gender = test.Gender.fillna('Male')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 105, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Married = train.Married.fillna('Yes')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 106, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Married = test.Married.fillna('Yes')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 107, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Dependents = train.Dependents.fillna('0')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 108, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Dependents = test.Dependents.fillna('0')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 109, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Self_Employed = train.Self_Employed.fillna('No')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 110, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Self_Employed = test.Self_Employed.fillna('No')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 111, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.LoanAmount = train.LoanAmount.fillna(train.LoanAmount.mean())" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 112, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.LoanAmount = test.LoanAmount.fillna(test.LoanAmount.mean())" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 113, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"360.0 512\n", | |
"180.0 44\n", | |
"480.0 15\n", | |
"300.0 13\n", | |
"84.0 4\n", | |
"240.0 4\n", | |
"120.0 3\n", | |
"36.0 2\n", | |
"60.0 2\n", | |
"12.0 1\n", | |
"Name: Loan_Amount_Term, dtype: int64" | |
] | |
}, | |
"execution_count": 113, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"train['Loan_Amount_Term'].value_counts()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 114, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Loan_Amount_Term = train.Loan_Amount_Term.fillna(360.0)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 115, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"360.0 311\n", | |
"180.0 22\n", | |
"480.0 8\n", | |
"300.0 7\n", | |
"240.0 4\n", | |
"84.0 3\n", | |
"6.0 1\n", | |
"120.0 1\n", | |
"36.0 1\n", | |
"350.0 1\n", | |
"12.0 1\n", | |
"60.0 1\n", | |
"Name: Loan_Amount_Term, dtype: int64" | |
] | |
}, | |
"execution_count": 115, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"test['Loan_Amount_Term'].value_counts()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 116, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Loan_Amount_Term = test.Loan_Amount_Term.fillna(360.0)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 117, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"1.0 475\n", | |
"0.0 89\n", | |
"Name: Credit_History, dtype: int64" | |
] | |
}, | |
"execution_count": 117, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"train['Credit_History'].value_counts()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 118, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"1.0 279\n", | |
"0.0 59\n", | |
"Name: Credit_History, dtype: int64" | |
] | |
}, | |
"execution_count": 118, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"test['Credit_History'].value_counts()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 119, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train.Credit_History = train.Credit_History.fillna(1.0) " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 120, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"test.Credit_History = test.Credit_History.fillna(1.0)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 121, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"Loan_ID 0\n", | |
"Gender 0\n", | |
"Married 0\n", | |
"Dependents 0\n", | |
"Education 0\n", | |
"Self_Employed 0\n", | |
"ApplicantIncome 0\n", | |
"CoapplicantIncome 0\n", | |
"LoanAmount 0\n", | |
"Loan_Amount_Term 0\n", | |
"Credit_History 0\n", | |
"Property_Area 0\n", | |
"Loan_Status 0\n", | |
"dtype: int64" | |
] | |
}, | |
"execution_count": 121, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"train.apply(lambda x: sum(x.isnull()),axis=0) #should be zero if all values are filled" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 122, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"Loan_ID 0\n", | |
"Gender 0\n", | |
"Married 0\n", | |
"Dependents 0\n", | |
"Education 0\n", | |
"Self_Employed 0\n", | |
"ApplicantIncome 0\n", | |
"CoapplicantIncome 0\n", | |
"LoanAmount 0\n", | |
"Loan_Amount_Term 0\n", | |
"Credit_History 0\n", | |
"Property_Area 0\n", | |
"dtype: int64" | |
] | |
}, | |
"execution_count": 122, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"test.apply(lambda x: sum(x.isnull()),axis=0)#should be zero if all values are filled" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 123, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Splitting traing data\n", | |
"X_train = train.iloc[:, 1: 12].values\n", | |
"y_train = train.iloc[:, 12].values" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 124, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"train, test = train_test_split(train, test_size=0.3, random_state=0)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 125, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([['Male', 'No', '0', ..., 360.0, 1.0, 'Urban'],\n", | |
" ['Male', 'Yes', '1', ..., 360.0, 1.0, 'Rural'],\n", | |
" ['Male', 'Yes', '0', ..., 360.0, 1.0, 'Urban'],\n", | |
" ...,\n", | |
" ['Male', 'Yes', '1', ..., 360.0, 1.0, 'Urban'],\n", | |
" ['Male', 'Yes', '2', ..., 360.0, 1.0, 'Urban'],\n", | |
" ['Female', 'No', '0', ..., 360.0, 0.0, 'Semiurban']], dtype=object)" | |
] | |
}, | |
"execution_count": 125, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"X_train" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 126, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n", | |
"labelencoder_X = LabelEncoder()\n", | |
"for i in range(0, 5):\n", | |
" X_train[:,i] = labelencoder_X.fit_transform(X_train[:,i])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 127, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stderr", | |
"output_type": "stream", | |
"text": [ | |
"C:\\Anaconda\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:415: FutureWarning: The handling of integer data will change in version 0.22. Currently, the categories are determined based on the range [0, max(values)], while in the future they will be determined based on the unique values.\n", | |
"If you want the future behaviour and silence this warning, you can specify \"categories='auto'\".\n", | |
"In case you used a LabelEncoder before this OneHotEncoder to convert the categories to integers, then you can now use the OneHotEncoder directly.\n", | |
" warnings.warn(msg, FutureWarning)\n", | |
"C:\\Anaconda\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:451: DeprecationWarning: The 'categorical_features' keyword is deprecated in version 0.20 and will be removed in 0.22. You can use the ColumnTransformer instead.\n", | |
" \"use the ColumnTransformer instead.\", DeprecationWarning)\n" | |
] | |
} | |
], | |
"source": [ | |
"X_train[:,9] = labelencoder_X.fit_transform(X_train[:,9])\n", | |
"X_train[:,10] = labelencoder_X.fit_transform(X_train[:,10])\n", | |
"onehotencoder = OneHotEncoder(categorical_features = [7])\n", | |
"X_train = onehotencoder.fit_transform(X_train).toarray()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 128, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"\n", | |
"# Encoding the Dependent Variable\n", | |
"labelencoder_y = LabelEncoder()\n", | |
"y_train = labelencoder_y.fit_transform(y_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 129, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([[ 0., 0., 0., ..., 360., 1., 2.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 0.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 2.],\n", | |
" ...,\n", | |
" [ 0., 0., 0., ..., 360., 1., 2.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 2.],\n", | |
" [ 0., 0., 0., ..., 360., 0., 1.]])" | |
] | |
}, | |
"execution_count": 129, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"\n", | |
"X_train" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 130, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1,\n", | |
" 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0,\n", | |
" 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1,\n", | |
" 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1,\n", | |
" 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1,\n", | |
" 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1,\n", | |
" 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0,\n", | |
" 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n", | |
" 1, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0,\n", | |
" 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1,\n", | |
" 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0,\n", | |
" 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0])" | |
] | |
}, | |
"execution_count": 130, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"\n", | |
"y_train" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 131, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Splitting traing data\n", | |
"X_test = test.iloc[:, 1: 12].values\n", | |
"y_test = test.iloc[:, 12].values" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 132, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"<class 'pandas.core.frame.DataFrame'>\n", | |
"Int64Index: 185 entries, 454 to 134\n", | |
"Data columns (total 13 columns):\n", | |
"Loan_ID 185 non-null object\n", | |
"Gender 185 non-null object\n", | |
"Married 185 non-null object\n", | |
"Dependents 185 non-null object\n", | |
"Education 185 non-null object\n", | |
"Self_Employed 185 non-null object\n", | |
"ApplicantIncome 185 non-null int64\n", | |
"CoapplicantIncome 185 non-null float64\n", | |
"LoanAmount 185 non-null float64\n", | |
"Loan_Amount_Term 185 non-null float64\n", | |
"Credit_History 185 non-null float64\n", | |
"Property_Area 185 non-null object\n", | |
"Loan_Status 185 non-null object\n", | |
"dtypes: float64(4), int64(1), object(8)\n", | |
"memory usage: 20.2+ KB\n" | |
] | |
} | |
], | |
"source": [ | |
"test.info()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 133, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stderr", | |
"output_type": "stream", | |
"text": [ | |
"C:\\Anaconda\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:415: FutureWarning: The handling of integer data will change in version 0.22. Currently, the categories are determined based on the range [0, max(values)], while in the future they will be determined based on the unique values.\n", | |
"If you want the future behaviour and silence this warning, you can specify \"categories='auto'\".\n", | |
"In case you used a LabelEncoder before this OneHotEncoder to convert the categories to integers, then you can now use the OneHotEncoder directly.\n", | |
" warnings.warn(msg, FutureWarning)\n", | |
"C:\\Anaconda\\lib\\site-packages\\sklearn\\preprocessing\\_encoders.py:451: DeprecationWarning: The 'categorical_features' keyword is deprecated in version 0.20 and will be removed in 0.22. You can use the ColumnTransformer instead.\n", | |
" \"use the ColumnTransformer instead.\", DeprecationWarning)\n" | |
] | |
} | |
], | |
"source": [ | |
"# Encoding categorical data\n", | |
"# Encoding the Independent Variable\n", | |
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n", | |
"labelencoder_X = LabelEncoder()\n", | |
"for i in range(0, 5):\n", | |
" X_test[:,i] = labelencoder_X.fit_transform(X_test[:,i])\n", | |
"X_test[:,9] = labelencoder_X.fit_transform(X_test[:,9])\n", | |
"X_test[:,10] = labelencoder_X.fit_transform(X_test[:,10])\n", | |
"\n", | |
"onehotencoder = OneHotEncoder(categorical_features = [7])\n", | |
"X_test = onehotencoder.fit_transform(X_test).toarray()\n", | |
"# Encoding the Dependent Variable\n", | |
"labelencoder_y = LabelEncoder()\n", | |
"y_test = labelencoder_y.fit_transform(y_test)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 134, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([[ 0., 0., 0., ..., 360., 1., 1.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 1.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 2.],\n", | |
" ...,\n", | |
" [ 0., 0., 1., ..., 360., 1., 1.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 0.],\n", | |
" [ 0., 0., 0., ..., 360., 1., 1.]])" | |
] | |
}, | |
"execution_count": 134, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"X_test" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 135, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0,\n", | |
" 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1,\n", | |
" 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 1])" | |
] | |
}, | |
"execution_count": 135, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"\n", | |
"y_test" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 136, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Feature Scaling\n", | |
"from sklearn.preprocessing import StandardScaler\n", | |
"sc = StandardScaler()\n", | |
"X_train = sc.fit_transform(X_train)\n", | |
"X_test = sc.fit_transform(X_test)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 137, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(185, 112)" | |
] | |
}, | |
"execution_count": 137, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"X_test.shape" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 138, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(614, 213)" | |
] | |
}, | |
"execution_count": 138, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"X_train.shape" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 139, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Applying PCA\n", | |
"from sklearn.decomposition import PCA\n", | |
"pca = PCA()\n", | |
"X_train = pca.fit_transform(X_train)\n", | |
"X_test = pca.fit_transform(X_test)\n", | |
"explained_variance = pca.explained_variance_ratio_" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 140, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Feature Scaling\n", | |
"from sklearn.preprocessing import StandardScaler\n", | |
"sc = StandardScaler()\n", | |
"X_train = sc.fit_transform(X_train)\n", | |
"X_test = sc.fit_transform(X_test)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 141, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stderr", | |
"output_type": "stream", | |
"text": [ | |
"C:\\Anaconda\\lib\\site-packages\\sklearn\\linear_model\\logistic.py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n", | |
" FutureWarning)\n" | |
] | |
} | |
], | |
"source": [ | |
"# Fitting Logistic Regression to the Training set\n", | |
"from sklearn.linear_model import LogisticRegression\n", | |
"classifier = LogisticRegression(random_state = 0)\n", | |
"classifier.fit(X_train, y_train)\n", | |
"y_pred = classifier.predict(X_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 142, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"y_pred = classifier.predict(X_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 143, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1,\n", | |
" 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0,\n", | |
" 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1,\n", | |
" 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n", | |
" 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0,\n", | |
" 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0])" | |
] | |
}, | |
"execution_count": 143, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"y_pred" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 144, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Predicting the Test set results\n", | |
"y_pred = classifier.predict(X_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 145, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"The accuracy of Logistic Regression is: 0.8811074918566775\n" | |
] | |
} | |
], | |
"source": [ | |
"from sklearn import metrics\n", | |
"print('The accuracy of Logistic Regression is: ', metrics.accuracy_score(y_pred, y_train))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 146, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n", | |
" metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n", | |
" weights='uniform')" | |
] | |
}, | |
"execution_count": 146, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"# Fitting K-NN to the Training set\n", | |
"from sklearn.neighbors import KNeighborsClassifier\n", | |
"classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)\n", | |
"classifier.fit(X_train, y_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 147, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"y_pred1 = classifier.predict(X_train)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 148, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1,\n", | |
" 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n", | |
" 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0,\n", | |
" 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0])" | |
] | |
}, | |
"execution_count": 148, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"y_pred1" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 149, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(614,)" | |
] | |
}, | |
"execution_count": 149, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"y_pred.shape" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 150, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"(614,)" | |
] | |
}, | |
"execution_count": 150, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"y_pred1.shape" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 151, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"final_pred = (y_pred+y_pred1)/2" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 152, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([0.5, 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 0. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 0. , 0. , 1. , 0. , 1. , 0.5, 0.5, 0. , 1. ,\n", | |
" 1. , 1. , 0. , 1. , 0. , 1. , 0. , 0.5, 0. , 1. , 0. , 1. , 1. ,\n", | |
" 1. , 0.5, 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 0.5, 1. , 0. , 1. , 1. , 0. , 1. , 1. , 1. , 0.5, 0. , 0. , 0.5,\n", | |
" 0. , 0.5, 1. , 1. , 0.5, 1. , 1. , 0.5, 0.5, 1. , 0.5, 0.5, 1. ,\n", | |
" 0.5, 1. , 1. , 1. , 0. , 0. , 1. , 1. , 1. , 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. , 1. , 0.5, 0.5, 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 0. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 0. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0. , 0.5, 0. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 1. , 1. , 0. ,\n", | |
" 1. , 1. , 1. , 0.5, 1. , 0.5, 1. , 1. , 0. , 1. , 0. , 0.5, 0. ,\n", | |
" 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. ,\n", | |
" 0. , 1. , 1. , 1. , 0. , 1. , 1. , 0.5, 0.5, 1. , 1. , 0. , 1. ,\n", | |
" 1. , 0. , 0. , 0. , 1. , 1. , 1. , 1. , 0.5, 1. , 0. , 0.5, 0.5,\n", | |
" 1. , 1. , 1. , 1. , 0.5, 0.5, 1. , 1. , 1. , 1. , 1. , 1. , 1. ,\n", | |
" 1. , 0. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 0.5, 1. , 1. ,\n", | |
" 1. , 0.5, 1. , 0. , 0.5, 1. , 1. , 0. , 1. , 0.5, 1. , 0. , 0.5,\n", | |
" 1. , 1. , 1. , 1. , 1. , 0. , 1. , 0.5, 0.5, 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 0.5, 1. , 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 0. , 1. , 0.5, 1. , 1. , 1. , 1. , 1. ,\n", | |
" 1. , 0.5, 0.5, 1. , 1. , 1. , 0. , 0. , 0.5, 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 0. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. ,\n", | |
" 0. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. ,\n", | |
" 0. , 1. , 0.5, 0. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 1. ,\n", | |
" 0. , 1. , 0. , 1. , 1. , 0.5, 0. , 0. , 1. , 1. , 1. , 1. , 1. ,\n", | |
" 1. , 0. , 1. , 0.5, 1. , 0. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 0. , 0.5, 0. , 1. ,\n", | |
" 1. , 0.5, 1. , 1. , 1. , 0. , 0. , 0. , 1. , 0. , 1. , 0. , 1. ,\n", | |
" 1. , 0. , 1. , 0.5, 1. , 0. , 1. , 0.5, 1. , 1. , 0. , 0.5, 1. ,\n", | |
" 1. , 1. , 0. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 0.5, 1. , 1. , 1. , 1. , 0.5, 0. , 0.5, 1. , 0. , 0.5, 1. ,\n", | |
" 1. , 1. , 0.5, 1. , 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 0.5, 1. ,\n", | |
" 1. , 1. , 1. , 0.5, 1. , 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 0. , 0. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 0. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 0. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5,\n", | |
" 0. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 1. ,\n", | |
" 0. , 1. , 0. , 1. , 0. , 1. , 1. , 0. , 0.5, 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 1. , 1. , 1. , 0. , 1. , 1. , 0. , 0. , 0.5, 1. , 0.5,\n", | |
" 1. , 1. , 1. , 1. , 0.5, 1. , 1. , 1. , 0. , 1. , 1. , 0. , 0. ,\n", | |
" 1. , 1. , 1. , 1. , 0. , 1. , 1. , 1. , 1. , 1. , 1. , 1. , 0.5,\n", | |
" 1. , 1. , 0. , 1. , 1. , 1. , 1. , 0.5, 0.5, 1. , 1. , 1. , 1. ,\n", | |
" 1. , 1. , 0. ])" | |
] | |
}, | |
"execution_count": 152, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"final_pred" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 153, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"[[0 1 1 1 1 1 1 0 1 0 1 1 1 1 1 1 1 0 0 1 0 1 0 0 0 1 1 1 0 1 0 1 0 0 0 1\n", | |
" 0 1 1 1 0 1 1 1 1 1 1 1 0 1 1 1 0 1 0 1 1 0 1 1 1 0 0 0 0 0 0 1 1 0 1 1\n", | |
" 0 0 1 0 0 1 0 1 1 1 0 0 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 0 0 1 1 1 1 1 1\n", | |
" 0 1 1 1 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 0 1 1 0 0 1 1 1 1\n", | |
" 1 1 1 1 1 1 0 0 0 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 0 1 1 1 0 1 0 1 1 0 1 0\n", | |
" 0 0 1 1 1 1 0 1 1 1 1 0 1 1 1 0 1 1 1 0 1 1 0 0 1 1 0 1 1 0 0 0 1 1 1 1\n", | |
" 0 1 0 0 0 1 1 1 1 0 0 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 0 1 0 1 1 1 0 1 0 0\n", | |
" 1 1 0 1 0 1 0 0 1 1 1 1 1 0 1 0 0 1 1 1 1 1 1 1 1 0 1 1 0 1 1 1 1 1 1 1\n", | |
" 1 1 1 0 1 0 1 1 1 1 1 1 0 0 1 1 1 0 0 0 1 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1\n", | |
" 1 0 1 1 1 0 1 1 1 1 1 1 1 1 0 1 0 0 1 1 1 1 0 1 1 1 1 0 1 0 1 1 0 0 0 1\n", | |
" 1 1 1 1 1 0 1 0 1 0 1 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 1 1\n", | |
" 0 1 1 0 0 0 1 1 0 1 1 1 0 0 0 1 0 1 0 1 1 0 1 0 1 0 1 0 1 1 0 0 1 1 1 0\n", | |
" 1 1 1 1 1 1 0 1 1 1 1 0 1 1 1 1 0 0 0 1 0 0 1 1 1 0 1 1 1 1 1 1 0 1 0 1\n", | |
" 1 1 1 0 1 1 1 1 1 0 1 1 1 1 1 1 1 1 0 0 1 1 0 1 1 1 0 1 1 1 1 0 1 1 1 0\n", | |
" 1 1 1 1 1 1 1 1 1 1 0 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 1 1 1 1 1 1\n", | |
" 1 0 1 1 1 1 0 1 0 1 0 1 1 0 0 1 1 1 1 1 1 1 1 1 0 1 1 0 0 0 1 0 1 1 1 1\n", | |
" 0 1 1 1 0 1 1 0 0 1 1 1 1 0 1 1 1 1 1 1 1 0 1 1 0 1 1 1 1 0 0 1 1 1 1 1\n", | |
" 1 0]]\n" | |
] | |
} | |
], | |
"source": [ | |
"mode = print(m[0])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 154, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"array([0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1,\n", | |
" 0, 0, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0,\n", | |
" 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,\n", | |
" 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1,\n", | |
" 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n", | |
" 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 0, 1, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0,\n", | |
" 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n", | |
" 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1,\n", | |
" 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0,\n", | |
" 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n", | |
" 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0],\n", | |
" dtype=int64)" | |
] | |
}, | |
"execution_count": 154, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"np.apply_along_axis(lambda x: np.bincount(x).argmax(), axis=0, arr=a)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.7.4" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment