{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport os\n\nsns.set_style('darkgrid')\nplt.style.use('seaborn-notebook')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.096802Z","iopub.execute_input":"2023-02-05T05:45:30.098563Z","iopub.status.idle":"2023-02-05T05:45:30.107995Z","shell.execute_reply.started":"2023-02-05T05:45:30.098475Z","shell.execute_reply":"2023-02-05T05:45:30.106562Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#read in train and test csv files to calculate descriptive stats and characteristics\n\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\n\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.110335Z","iopub.execute_input":"2023-02-05T05:45:30.111126Z","iopub.status.idle":"2023-02-05T05:45:30.284930Z","shell.execute_reply.started":"2023-02-05T05:45:30.111085Z","shell.execute_reply":"2023-02-05T05:45:30.283763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.286527Z","iopub.execute_input":"2023-02-05T05:45:30.287156Z","iopub.status.idle":"2023-02-05T05:45:30.318632Z","shell.execute_reply.started":"2023-02-05T05:45:30.287115Z","shell.execute_reply":"2023-02-05T05:45:30.317350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.shape","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.320704Z","iopub.execute_input":"2023-02-05T05:45:30.321762Z","iopub.status.idle":"2023-02-05T05:45:30.331969Z","shell.execute_reply.started":"2023-02-05T05:45:30.321707Z","shell.execute_reply":"2023-02-05T05:45:30.330170Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.336712Z","iopub.execute_input":"2023-02-05T05:45:30.337334Z","iopub.status.idle":"2023-02-05T05:45:30.379342Z","shell.execute_reply.started":"2023-02-05T05:45:30.337293Z","shell.execute_reply":"2023-02-05T05:45:30.378344Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.describe()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.380784Z","iopub.execute_input":"2023-02-05T05:45:30.381954Z","iopub.status.idle":"2023-02-05T05:45:30.416549Z","shell.execute_reply.started":"2023-02-05T05:45:30.381900Z","shell.execute_reply":"2023-02-05T05:45:30.414648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax1 = sns.countplot(data=train, x='anatom_site_general_challenge')\nax1.set_title('Distribution of Anatomical Sites Training Set')\nax1.tick_params(axis='x', labelrotation = 45, labelsize = 12)\n\n#note: largest category by far is the torso, oral/genital is the least common category","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.418517Z","iopub.execute_input":"2023-02-05T05:45:30.418949Z","iopub.status.idle":"2023-02-05T05:45:30.704629Z","shell.execute_reply.started":"2023-02-05T05:45:30.418915Z","shell.execute_reply":"2023-02-05T05:45:30.703196Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax2 = sns.countplot(data=train, x='sex')\nax2.set_title('Distribution of Gender')\n\n#note: gender is pretty evenly distributed amongst the image dataset","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.707297Z","iopub.execute_input":"2023-02-05T05:45:30.707829Z","iopub.status.idle":"2023-02-05T05:45:30.932467Z","shell.execute_reply.started":"2023-02-05T05:45:30.707791Z","shell.execute_reply":"2023-02-05T05:45:30.931302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax3 = sns.countplot(data=train, x='diagnosis')\nax3.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax3.set_title('Distribution of Diagnosis')\n\n#note: the vast majority of the images have no associated diagnosis, some have the nevus diagnosis, and very few have the melanoma diagnosis. \n#Melanoma is the target we're actually looking for.","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:30.933939Z","iopub.execute_input":"2023-02-05T05:45:30.934605Z","iopub.status.idle":"2023-02-05T05:45:31.259688Z","shell.execute_reply.started":"2023-02-05T05:45:30.934566Z","shell.execute_reply":"2023-02-05T05:45:31.258683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax4 = sns.countplot(data=train, x='benign_malignant')\nax4.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax4.set_title('Distribution of Diagnosis')\n\n#note: malignant here is defined as a have a \"melanoma\" disease label","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.261091Z","iopub.execute_input":"2023-02-05T05:45:31.261634Z","iopub.status.idle":"2023-02-05T05:45:31.500372Z","shell.execute_reply.started":"2023-02-05T05:45:31.261602Z","shell.execute_reply":"2023-02-05T05:45:31.499148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax5 = sns.histplot(data=train, x='age_approx', bins=18)\nax5.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax5.set_title('Distribution of Age')\n\n#age follows a normal distribution","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.501847Z","iopub.execute_input":"2023-02-05T05:45:31.502198Z","iopub.status.idle":"2023-02-05T05:45:31.814826Z","shell.execute_reply.started":"2023-02-05T05:45:31.502168Z","shell.execute_reply":"2023-02-05T05:45:31.813838Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('n rows where target != benign_malignant: {}'.format(len(train.loc[(train['target'] == 1) & (train['benign_malignant'] != 'malignant')])))\nprint('n rows where benign_malignant != melanoma diagnosis: {}'.format(len(train.loc[(train['diagnosis'] != 'melanoma') & (train['benign_malignant'] == 'malignant')])))\nprint('n rows where target != benign_malignant: {}'.format(len(train.loc[(train['target'] == 1) & (train['benign_malignant'] != 'malignant')])))\n\n#my assumptions hold--this dataset is labeled based off of the 'melanoma' diagnosis, \n#and a positive value in the target column indicates a malignant melanoma tumor","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.816110Z","iopub.execute_input":"2023-02-05T05:45:31.816466Z","iopub.status.idle":"2023-02-05T05:45:31.840663Z","shell.execute_reply.started":"2023-02-05T05:45:31.816433Z","shell.execute_reply":"2023-02-05T05:45:31.839232Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print the number of missing values from each col in train\nfor col in train.columns:\n    print(col + ' missing values: ' + str(train[col].isna().sum()))\n    ","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.843087Z","iopub.execute_input":"2023-02-05T05:45:31.843573Z","iopub.status.idle":"2023-02-05T05:45:31.864345Z","shell.execute_reply.started":"2023-02-05T05:45:31.843525Z","shell.execute_reply":"2023-02-05T05:45:31.863132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Pull out just the observations that are positive for the target condition\nmalignant = train[train['target'] == 1]\nprint(malignant.head())\nprint(malignant.shape)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.870531Z","iopub.execute_input":"2023-02-05T05:45:31.870938Z","iopub.status.idle":"2023-02-05T05:45:31.890153Z","shell.execute_reply.started":"2023-02-05T05:45:31.870906Z","shell.execute_reply":"2023-02-05T05:45:31.888481Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for col in malignant.columns:\n    print(col + ' missing values: ' + str(malignant[col].isna().sum()))\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.892358Z","iopub.execute_input":"2023-02-05T05:45:31.892919Z","iopub.status.idle":"2023-02-05T05:45:31.909161Z","shell.execute_reply.started":"2023-02-05T05:45:31.892870Z","shell.execute_reply":"2023-02-05T05:45:31.907408Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#fill missing anatom site values with \"unknown or other\"\ntrain.anatom_site_general_challenge.fillna('other or unknown', inplace=True)\n\n#verify there are no more missing values in that column\nprint('anatom_site_general_challenge' + ' missing values: ' + str(train['anatom_site_general_challenge'].isna().sum()))\n\n#plot the new distribution\nax = sns.countplot(data=train, x='anatom_site_general_challenge')\n#train.anatom_site_general_challenge.hist()\nax.set_title('Distribution of Anatomical Sites Training Set')\nax.tick_params(axis='x', labelrotation = 45, labelsize = 12)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:31.911462Z","iopub.execute_input":"2023-02-05T05:45:31.911941Z","iopub.status.idle":"2023-02-05T05:45:32.234885Z","shell.execute_reply.started":"2023-02-05T05:45:31.911898Z","shell.execute_reply":"2023-02-05T05:45:32.233434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Test Set exploration**","metadata":{}},{"cell_type":"code","source":"test.head()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.236408Z","iopub.execute_input":"2023-02-05T05:45:32.236889Z","iopub.status.idle":"2023-02-05T05:45:32.253949Z","shell.execute_reply.started":"2023-02-05T05:45:32.236854Z","shell.execute_reply":"2023-02-05T05:45:32.252401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.shape","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.255922Z","iopub.execute_input":"2023-02-05T05:45:32.256622Z","iopub.status.idle":"2023-02-05T05:45:32.268666Z","shell.execute_reply.started":"2023-02-05T05:45:32.256559Z","shell.execute_reply":"2023-02-05T05:45:32.266623Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print the number of missing values from each col in train\nfor col in test.columns:\n    print(col + ' missing values: ' + str(test[col].isna().sum()))\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.270421Z","iopub.execute_input":"2023-02-05T05:45:32.270915Z","iopub.status.idle":"2023-02-05T05:45:32.287630Z","shell.execute_reply.started":"2023-02-05T05:45:32.270867Z","shell.execute_reply":"2023-02-05T05:45:32.286156Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#how many images are associated with each patient?\nindividuals_count = train.groupby('patient_id').count()\n\nindividuals_count.head()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.289572Z","iopub.execute_input":"2023-02-05T05:45:32.290099Z","iopub.status.idle":"2023-02-05T05:45:32.335314Z","shell.execute_reply.started":"2023-02-05T05:45:32.290048Z","shell.execute_reply":"2023-02-05T05:45:32.332763Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#show the disribution of image counts\nfig, ax = plt.subplots(figsize=(25,10))\nax = sns.histplot(data=individuals_count, x='image_name')\nax.set_title('Images per Patient')\nax.set_xlabel('Unique Images per Patient')\nax.set_ylabel('Number of Patients')\nax.set_xticks(ticks=range(0,120,10))\n\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.338179Z","iopub.execute_input":"2023-02-05T05:45:32.338691Z","iopub.status.idle":"2023-02-05T05:45:32.823783Z","shell.execute_reply.started":"2023-02-05T05:45:32.338645Z","shell.execute_reply":"2023-02-05T05:45:32.822858Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('the mean number of images per patient is: {}'.format(round(individuals_count.image_name.mean(),2)))\nprint('the median number of images per patient is: {}'.format(round(individuals_count.image_name.median(),2)))\nprint('the standard deviation of the number of images per patient is: {}'.format(round(individuals_count.image_name.std(),2)))","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.824893Z","iopub.execute_input":"2023-02-05T05:45:32.825741Z","iopub.status.idle":"2023-02-05T05:45:32.837725Z","shell.execute_reply.started":"2023-02-05T05:45:32.825707Z","shell.execute_reply":"2023-02-05T05:45:32.836484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#check out the distribution of positive cases grouped by patient\nindividuals_sum = train.groupby('patient_id').sum()\n\nprint(individuals_sum.target.describe())\n\n#fig, ax = plt.subplots(figsize=(18,10))\nax = sns.histplot(data=individuals_sum, x='target', bins=10)\nax.set_title('Quantity of Malignant Tumors per Patient')\nax.set_xlabel('Sum of Positives')\nax.set_ylabel('Number of Patients')\n#ax.set_xticks(ticks=range(0,20))\n\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:32.839619Z","iopub.execute_input":"2023-02-05T05:45:32.841231Z","iopub.status.idle":"2023-02-05T05:45:33.203668Z","shell.execute_reply.started":"2023-02-05T05:45:32.841183Z","shell.execute_reply":"2023-02-05T05:45:33.201665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Another pass at missing sex and age values**","metadata":{}},{"cell_type":"code","source":"#let's pull out individuals from individuals_count who have fewer counts of sex or age_approx than image_name\nindividuals_count.loc[(individuals_count['sex'] < individuals_count['image_name']) | (individuals_count['age_approx'] < individuals_count['image_name'])]","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.206659Z","iopub.execute_input":"2023-02-05T05:45:33.207203Z","iopub.status.idle":"2023-02-05T05:45:33.225299Z","shell.execute_reply.started":"2023-02-05T05:45:33.207156Z","shell.execute_reply":"2023-02-05T05:45:33.223427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pats = ['IP_0550106','IP_5205991', 'IP_9835712']\nindividuals_sum.reset_index(inplace=True)\n\n\nindividuals_sum.query('patient_id in @pats')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.227456Z","iopub.execute_input":"2023-02-05T05:45:33.228728Z","iopub.status.idle":"2023-02-05T05:45:33.250587Z","shell.execute_reply.started":"2023-02-05T05:45:33.228670Z","shell.execute_reply":"2023-02-05T05:45:33.248910Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('percentage of missing patient data= {}%'.format(round((3+48+17)/len(train)*100,2)))","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.252176Z","iopub.execute_input":"2023-02-05T05:45:33.252982Z","iopub.status.idle":"2023-02-05T05:45:33.260521Z","shell.execute_reply.started":"2023-02-05T05:45:33.252927Z","shell.execute_reply":"2023-02-05T05:45:33.259083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#drop all rows from the train dataframe that are associated with the 3 patients identified above.\ntrain.drop(train[(train['patient_id'] == 'IP_0550106') | (train['patient_id'] == 'IP_5205991') |(train['patient_id'] == 'IP_9835712')].index, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.262555Z","iopub.execute_input":"2023-02-05T05:45:33.263033Z","iopub.status.idle":"2023-02-05T05:45:33.288775Z","shell.execute_reply.started":"2023-02-05T05:45:33.262990Z","shell.execute_reply":"2023-02-05T05:45:33.287306Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#check for any more missing values:\nfor col in train.columns:\n    print(col + ' missing values: ' + str(train[col].isna().sum()))","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.291325Z","iopub.execute_input":"2023-02-05T05:45:33.291691Z","iopub.status.idle":"2023-02-05T05:45:33.316283Z","shell.execute_reply.started":"2023-02-05T05:45:33.291660Z","shell.execute_reply":"2023-02-05T05:45:33.314625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Relationships between positive cases and other variables.**","metadata":{}},{"cell_type":"code","source":"#make sure index is the patient id so we can join these aggregate dfs\n\nindividuals_sum.set_index('patient_id', inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.318265Z","iopub.execute_input":"2023-02-05T05:45:33.319108Z","iopub.status.idle":"2023-02-05T05:45:33.326880Z","shell.execute_reply.started":"2023-02-05T05:45:33.319038Z","shell.execute_reply":"2023-02-05T05:45:33.325238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"patients = individuals_count.join(individuals_sum, lsuffix='_count', rsuffix='_sum')\npatients.drop(columns=['sex','age_approx_count','anatom_site_general_challenge','diagnosis', 'benign_malignant','target_count', 'age_approx_sum'], inplace=True)\npatients.rename(columns={'image_name':'n_images'}, inplace=True)\npatients.head()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.329273Z","iopub.execute_input":"2023-02-05T05:45:33.329862Z","iopub.status.idle":"2023-02-05T05:45:33.352778Z","shell.execute_reply.started":"2023-02-05T05:45:33.329814Z","shell.execute_reply":"2023-02-05T05:45:33.351234Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#join with train df to include sex and age data for each patient\npatients = patients.join(train.set_index('patient_id'), on='patient_id')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.354406Z","iopub.execute_input":"2023-02-05T05:45:33.354764Z","iopub.status.idle":"2023-02-05T05:45:33.388386Z","shell.execute_reply.started":"2023-02-05T05:45:33.354734Z","shell.execute_reply":"2023-02-05T05:45:33.387112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#clean it up\npatients.reset_index(inplace=True)\npatients.drop_duplicates(subset='patient_id', inplace=True)\npatients.drop(columns=['image_name','anatom_site_general_challenge', 'diagnosis',   'benign_malignant', 'target'], inplace=True)\npatients.head()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.390046Z","iopub.execute_input":"2023-02-05T05:45:33.390594Z","iopub.status.idle":"2023-02-05T05:45:33.426374Z","shell.execute_reply.started":"2023-02-05T05:45:33.390549Z","shell.execute_reply":"2023-02-05T05:45:33.424816Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot n_images v. target_sum\nax1 = sns.scatterplot(data=patients, x='n_images', y ='target_sum', hue='sex')\nax1.set_title('n_images per patient v. target_sum')\n#ax1.tick_params(axis='x', labelrotation = 45, labelsize = 12)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.428289Z","iopub.execute_input":"2023-02-05T05:45:33.429186Z","iopub.status.idle":"2023-02-05T05:45:33.876210Z","shell.execute_reply.started":"2023-02-05T05:45:33.429139Z","shell.execute_reply":"2023-02-05T05:45:33.875170Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax1 = sns.violinplot(data=patients, y='n_images', x ='target_sum')\nax1.set_title('n_images per patient v. target_sum')\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:33.880476Z","iopub.execute_input":"2023-02-05T05:45:33.880897Z","iopub.status.idle":"2023-02-05T05:45:34.273039Z","shell.execute_reply.started":"2023-02-05T05:45:33.880861Z","shell.execute_reply":"2023-02-05T05:45:34.271421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ax1 = sns.stripplot(data=patients, y='target_sum', x ='sex')\nax1.set_title('target_sum distribution by gender')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:34.275343Z","iopub.execute_input":"2023-02-05T05:45:34.275881Z","iopub.status.idle":"2023-02-05T05:45:34.519864Z","shell.execute_reply.started":"2023-02-05T05:45:34.275830Z","shell.execute_reply":"2023-02-05T05:45:34.518849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot age_approx v target_sum\nax1 = sns.stripplot(data=patients, x='age_approx', y ='target_sum')\nax1.set_title('age_approx v. target_sum')\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:34.521230Z","iopub.execute_input":"2023-02-05T05:45:34.522303Z","iopub.status.idle":"2023-02-05T05:45:34.975226Z","shell.execute_reply.started":"2023-02-05T05:45:34.522259Z","shell.execute_reply":"2023-02-05T05:45:34.973607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot n_images v. target_sum\nax1 = sns.histplot(data=patients, x='age_approx', bins=16)\nax1.set_title('Ditribution of Patient Ages in Dataset')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:34.977082Z","iopub.execute_input":"2023-02-05T05:45:34.977623Z","iopub.status.idle":"2023-02-05T05:45:35.321569Z","shell.execute_reply.started":"2023-02-05T05:45:34.977576Z","shell.execute_reply":"2023-02-05T05:45:35.320216Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Visualizing Images**\n","metadata":{}},{"cell_type":"code","source":"#open one image\n\n#import ImageIO\nimport imageio.v2 as imageio\n\n#load an image\nim = imageio.imread('../input/siim-isic-melanoma-classification/jpeg/train/ISIC_0015719.jpg')\n\n#plot image\nplt.imshow(im)\nplt.axis('off')\n#plt.show()\n\n#print metadata\nprint(im.meta.keys())","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:35.323559Z","iopub.execute_input":"2023-02-05T05:45:35.325560Z","iopub.status.idle":"2023-02-05T05:45:40.045232Z","shell.execute_reply.started":"2023-02-05T05:45:35.325514Z","shell.execute_reply":"2023-02-05T05:45:40.044071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Plot malignant lesions**","metadata":{}},{"cell_type":"code","source":"#Now, let's see if we can show all the malignant images\n\n#make a list of image names that have the malignant target value = 1\nmal_ims = train[train['target']==1].image_name\n\n#convert those image names into path names to access each photo\n#mal_im_paths = ['../input/siim-isic-melanoma-classification/jpeg/train/' + str(im) + '.jpg' for im in mal_ims]","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:40.046515Z","iopub.execute_input":"2023-02-05T05:45:40.046905Z","iopub.status.idle":"2023-02-05T05:45:40.056803Z","shell.execute_reply.started":"2023-02-05T05:45:40.046869Z","shell.execute_reply":"2023-02-05T05:45:40.055021Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot all malignant images\n\nfig, axs = plt.subplots(nrows=146, ncols=4, tight_layout=True, figsize=(15,365))\nfig.suptitle('Malignant Lesions', fontsize=14)\n\nfor ax, image in zip(axs.ravel(), mal_ims):\n    path = '../input/siim-isic-melanoma-classification/jpeg/train/' + str(image) + '.jpg'\n    im = imageio.imread(path)\n    ax.imshow(im)\n    ax.axis('off')\n    ax.set_title(image)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:45:40.058343Z","iopub.execute_input":"2023-02-05T05:45:40.058921Z","iopub.status.idle":"2023-02-05T05:56:55.599470Z","shell.execute_reply.started":"2023-02-05T05:45:40.058886Z","shell.execute_reply":"2023-02-05T05:56:55.598148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import random\nrandom.seed(42)\n\n#make a list of image names that have the malignant target value = 0\nben_ims = train[train['target']==0].image_name\n\n#take a random sample of 100 of these images\nrand_ben_ims = random.sample(list(ben_ims),100)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:56:55.614297Z","iopub.execute_input":"2023-02-05T05:56:55.614758Z","iopub.status.idle":"2023-02-05T05:56:55.645118Z","shell.execute_reply.started":"2023-02-05T05:56:55.614722Z","shell.execute_reply":"2023-02-05T05:56:55.643528Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#plot the subset of 100 benign images\n\nfig, axs = plt.subplots(nrows=25, ncols=4, tight_layout=True, figsize=(15,62.5))\nfig.suptitle('Subset of Benign Lesions', fontsize=14, y=0.98)\n\nfor ax, image in zip(axs.ravel(), rand_ben_ims):\n    path = '../input/siim-isic-melanoma-classification/jpeg/train/' + str(image) + '.jpg'\n    im = imageio.imread(path)\n    ax.imshow(im)\n    ax.axis('off')\n    ax.set_title(image)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T05:56:55.646927Z","iopub.execute_input":"2023-02-05T05:56:55.647510Z","iopub.status.idle":"2023-02-05T06:00:06.212717Z","shell.execute_reply.started":"2023-02-05T05:56:55.647446Z","shell.execute_reply":"2023-02-05T06:00:06.211475Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# System\nimport cv2\nimport os, os.path\nfrom PIL import Image             \nimport gc\nimport time\nimport datetime\n\n# Basics\nimport pandas as pd\nimport numpy as np\nimport random\nimport seaborn as sns\nimport matplotlib\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom tqdm.notebook import tqdm     \n\n# SKlearn\nfrom sklearn.model_selection import StratifiedKFold, GroupKFold\nfrom sklearn.metrics import accuracy_score, roc_auc_score, confusion_matrix\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn import preprocessing\n\nfrom skimage import io\n\n# PyTorch\nimport torch\nimport torchvision\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import Dataset, DataLoader, Subset\n\nfrom torchvision.models import resnet34\nfrom torchvision import transforms\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nprint(\"PyTorch Version: \",torch.__version__)\nprint(\"Torchvision Version: \",torchvision.__version__)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:06.214351Z","iopub.execute_input":"2023-02-05T06:00:06.214941Z","iopub.status.idle":"2023-02-05T06:00:09.630094Z","shell.execute_reply.started":"2023-02-05T06:00:06.214905Z","shell.execute_reply":"2023-02-05T06:00:09.627611Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# For reproducibility\nseed = 1234\n\nnp.random.seed(seed)\nrandom.seed(seed)\ntorch.manual_seed(seed)\ntorch.cuda.manual_seed(seed)\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.632495Z","iopub.execute_input":"2023-02-05T06:00:09.633636Z","iopub.status.idle":"2023-02-05T06:00:09.645879Z","shell.execute_reply.started":"2023-02-05T06:00:09.633570Z","shell.execute_reply":"2023-02-05T06:00:09.644545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nprint('Device available now:', device)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.648222Z","iopub.execute_input":"2023-02-05T06:00:09.649336Z","iopub.status.idle":"2023-02-05T06:00:09.662455Z","shell.execute_reply.started":"2023-02-05T06:00:09.649279Z","shell.execute_reply":"2023-02-05T06:00:09.660399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')[1:1000]\n# train_df = train_df.head(1000)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.664599Z","iopub.execute_input":"2023-02-05T06:00:09.666401Z","iopub.status.idle":"2023-02-05T06:00:09.736761Z","shell.execute_reply.started":"2023-02-05T06:00:09.666315Z","shell.execute_reply":"2023-02-05T06:00:09.734929Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.target.value_counts()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.738846Z","iopub.execute_input":"2023-02-05T06:00:09.739353Z","iopub.status.idle":"2023-02-05T06:00:09.751716Z","shell.execute_reply.started":"2023-02-05T06:00:09.739317Z","shell.execute_reply":"2023-02-05T06:00:09.749985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(train_df)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.753930Z","iopub.execute_input":"2023-02-05T06:00:09.754387Z","iopub.status.idle":"2023-02-05T06:00:09.765518Z","shell.execute_reply.started":"2023-02-05T06:00:09.754355Z","shell.execute_reply":"2023-02-05T06:00:09.764422Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class MelanomaDataset(Dataset):\n    \n    def __init__(self, dataframe,is_train=True, is_valid=False, is_test=False):\n        self.dataframe, self.is_train, self.is_valid = dataframe, is_train, is_valid\n        \n        # Data Augmentation\n        if is_train or is_test:\n            self.transform = transforms.Compose([transforms.ToPILImage(),\n                                                 transforms.RandomResizedCrop((224,224), scale=(0.4, 1.0)),\n                                                 transforms.RandomHorizontalFlip(p = 0.3),\n                                                 transforms.RandomVerticalFlip(p = 0.3),\n                                                 transforms.ToTensor(),\n                                                 transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])\n        else:\n            self.transform = transforms.Compose([transforms.ToPILImage(),\n                                                 transforms.Resize((224,224)),\n                                                 transforms.ToTensor(),\n                                                 transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])\n            \n    def __len__(self):\n        return len(self.dataframe)\n    \n    def __getitem__(self, index):\n        # Select path and read image\n        img_name = self.dataframe['image_name'][index]\n        image_path = f'../input/siim-isic-melanoma-classification/jpeg/train/{img_name}.jpg'\n        image = io.imread(image_path)\n        \n        # Apply transforms\n        image = self.transform(image)\n\n        \n        # If train/valid: image + class | If test: only image\n        if self.is_train or self.is_valid:\n            return (image, self.dataframe['target'][index])\n        else:\n            return (image)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.767991Z","iopub.execute_input":"2023-02-05T06:00:09.768449Z","iopub.status.idle":"2023-02-05T06:00:09.782174Z","shell.execute_reply.started":"2023-02-05T06:00:09.768415Z","shell.execute_reply":"2023-02-05T06:00:09.780434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(resnet34(pretrained=True))","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:09.784043Z","iopub.execute_input":"2023-02-05T06:00:09.784685Z","iopub.status.idle":"2023-02-05T06:00:19.701809Z","shell.execute_reply.started":"2023-02-05T06:00:09.784640Z","shell.execute_reply":"2023-02-05T06:00:19.700768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class ResNet34Network(nn.Module):\n    def __init__(self):\n        super().__init__()\n        \n        # Define Feature part (IMAGE)\n        self.features = resnet34(pretrained=True) # 1000 neurons out\n        \n        for param in self.features.parameters():\n            param.requires_grad = False\n  \n        # Define Classification part\n        self.classification = nn.Linear(1000, 1)\n        \n        \n    def forward(self, image):\n        # Image CNN\n        image = self.features(image)\n        \n        # Classifier\n        out = self.classification(image)\n        \n        return out","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:19.703876Z","iopub.execute_input":"2023-02-05T06:00:19.704951Z","iopub.status.idle":"2023-02-05T06:00:19.713347Z","shell.execute_reply.started":"2023-02-05T06:00:19.704906Z","shell.execute_reply":"2023-02-05T06:00:19.711580Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = ResNet34Network()\nmodel = model.to(device)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:19.716008Z","iopub.execute_input":"2023-02-05T06:00:19.716678Z","iopub.status.idle":"2023-02-05T06:00:20.185750Z","shell.execute_reply.started":"2023-02-05T06:00:19.716631Z","shell.execute_reply":"2023-02-05T06:00:20.183959Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(model)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.187983Z","iopub.execute_input":"2023-02-05T06:00:20.189659Z","iopub.status.idle":"2023-02-05T06:00:20.200890Z","shell.execute_reply.started":"2023-02-05T06:00:20.189593Z","shell.execute_reply":"2023-02-05T06:00:20.198989Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Data object and Loader\ndataset = MelanomaDataset(train_df, is_train=True, is_valid=False, is_test=False)\nloader = DataLoader(dataset,batch_size=3, shuffle=True)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.202768Z","iopub.execute_input":"2023-02-05T06:00:20.203193Z","iopub.status.idle":"2023-02-05T06:00:20.218526Z","shell.execute_reply.started":"2023-02-05T06:00:20.203157Z","shell.execute_reply":"2023-02-05T06:00:20.216586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Get a sample\nfor image, labels in loader:\n    image_example = image\n    labels_example = torch.tensor(labels, dtype=torch.float32)\n    break\n    \nprint('Data shape:', image_example.shape)\nprint('Label:', labels_example)\n","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.220683Z","iopub.execute_input":"2023-02-05T06:00:20.221407Z","iopub.status.idle":"2023-02-05T06:00:20.824120Z","shell.execute_reply.started":"2023-02-05T06:00:20.221341Z","shell.execute_reply":"2023-02-05T06:00:20.822301Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"learning_rate = 0.0005\nepochs = 5\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.826031Z","iopub.execute_input":"2023-02-05T06:00:20.826572Z","iopub.status.idle":"2023-02-05T06:00:20.834125Z","shell.execute_reply.started":"2023-02-05T06:00:20.826531Z","shell.execute_reply":"2023-02-05T06:00:20.832441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Initiate the model\nmodel = model\nmodel = model.to(device)\noptimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr = learning_rate)\ncriterion = nn.BCEWithLogitsLoss()  ","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.835510Z","iopub.execute_input":"2023-02-05T06:00:20.835894Z","iopub.status.idle":"2023-02-05T06:00:20.851235Z","shell.execute_reply.started":"2023-02-05T06:00:20.835862Z","shell.execute_reply":"2023-02-05T06:00:20.849390Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_size = int(len(train_df) * 0.6)\nval_size = int(len(train_df) * 0.2)\ntest_size = int(len(train_df) * 0.2)\n\nprint(f'train size : {train_size}, val size : {val_size}, test size : {test_size}')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.854225Z","iopub.execute_input":"2023-02-05T06:00:20.854857Z","iopub.status.idle":"2023-02-05T06:00:20.863645Z","shell.execute_reply.started":"2023-02-05T06:00:20.854808Z","shell.execute_reply":"2023-02-05T06:00:20.862446Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# --- Read in Data ---\ntrain_data = train_df.iloc[:train_size].reset_index(drop=True)\nvalid_data = train_df.iloc[train_size:train_size + val_size].reset_index(drop=True)\ntest_data = train_df.iloc[train_size + val_size:].reset_index(drop=True)\n# Create Data instances\ntrain = MelanomaDataset(train_data, is_train=True, is_valid=False, is_test=False)\nvalid = MelanomaDataset(valid_data, is_train=False, is_valid=True, is_test=False)\ntest = MelanomaDataset(valid_data, is_train=False, is_valid=True, is_test=False)\n\n# Dataloaders\ntrain_loader = DataLoader(train, batch_size=16, shuffle=True)\nvalid_loader = DataLoader(valid, batch_size=8, shuffle=True)\ntest_loader = DataLoader(valid, batch_size=1, shuffle=True)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.865245Z","iopub.execute_input":"2023-02-05T06:00:20.865909Z","iopub.status.idle":"2023-02-05T06:00:20.881965Z","shell.execute_reply.started":"2023-02-05T06:00:20.865869Z","shell.execute_reply":"2023-02-05T06:00:20.880156Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# === EPOCHS ===\nfor epoch in range(epochs):\n    print(f'epoch : {epoch} start!')\n    start_time = time.time()\n    correct = 0\n    train_losses = 0\n\n    # === TRAIN ===\n    # Sets the module in training mode.\n    model.train()\n\n    for images, labels in train_loader:\n        # Save them to device\n        images = torch.tensor(images, device=device, dtype=torch.float32)\n        labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n        # Clear gradients first; very important, usually done BEFORE prediction\n        optimizer.zero_grad()\n\n        # Log Probabilities & Backpropagation\n        out = model(images)\n        loss = criterion(out, labels.unsqueeze(1))\n        loss.backward()\n        optimizer.step()\n\n        train_losses += loss.item()\n        # From log probabilities to actual probabilities\n        train_preds = torch.round(torch.sigmoid(out)) # 0 and 1\n        # Number of correct predictions\n        correct += (train_preds.cpu() == labels.cpu().unsqueeze(1)).sum().item()\n\n    # Compute Train Accuracy\n    train_acc = correct*100 / train_size\n    print(f'Epoch :{epoch + 1} - train accuracy: {train_acc}')\n    \n    # === EVAL ===\n    model.eval()\n\n    # Create matrix to store evaluation predictions (for accuracy)\n    valid_preds = torch.zeros(size = (len(valid_data), 1), device=device, dtype=torch.float32)\n\n\n    # Disables gradients (we need to be sure no optimization happens)\n    with torch.no_grad():\n        for k, (images, labels) in enumerate(valid_loader):\n            images = torch.tensor(images, device=device, dtype=torch.float32)\n            labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n            out = model(images)\n            pred = torch.sigmoid(out)\n            valid_preds[k*images.shape[0] : k*images.shape[0] + images.shape[0]] = pred\n\n        # Compute accuracy\n        valid_acc = accuracy_score(valid_data['target'].values, \n                                           torch.round(valid_preds.cpu()))*100\n        \n        # Compute ROC\n        valid_roc = roc_auc_score(valid_data['target'].values, \n                                          valid_preds.cpu())\n\n        # Compute time on Train + Eval\n        duration = str(datetime.timedelta(seconds=time.time() - start_time))[:7]\n\n\n        # PRINT INFO\n        print('{} | Epoch: {}/{} | Loss: {:.4} | Train Acc: {:.3} | Valid Acc: {:.3} ROC: {:.3}'.\\\n                    format(duration, epoch+1, epochs, train_losses, train_acc, valid_acc,valid_roc))\n        \n        \ntorch.save(model.state_dict(), './model.pt')\n\nfrom IPython.display import FileLink\nFileLink(r'model.pt')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:00:20.884375Z","iopub.execute_input":"2023-02-05T06:00:20.884827Z","iopub.status.idle":"2023-02-05T06:29:00.965316Z","shell.execute_reply.started":"2023-02-05T06:00:20.884790Z","shell.execute_reply":"2023-02-05T06:29:00.962996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def check_accuracy(loader, model):\n    num_correct = 0\n    num_samples = 0\n    model.eval()\n    \n    with torch.no_grad():\n        for x, y in loader:\n            x = x.to(device=device)\n            y = y.to(device=device)\n            \n            scores = model(x)\n            _, predictions = scores.max(1)\n            num_correct += (predictions == y).sum()\n            num_samples += predictions.size(0)\n        \n        print(f'Got {num_correct} / {num_samples} with Test Accuracy {float(num_correct)/float(num_samples)*100:.2f}') ","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:29:00.968454Z","iopub.execute_input":"2023-02-05T06:29:00.969131Z","iopub.status.idle":"2023-02-05T06:29:00.980603Z","shell.execute_reply.started":"2023-02-05T06:29:00.969074Z","shell.execute_reply":"2023-02-05T06:29:00.979019Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"check_accuracy(test_loader,model)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:29:00.982713Z","iopub.execute_input":"2023-02-05T06:29:00.983338Z","iopub.status.idle":"2023-02-05T06:30:37.877048Z","shell.execute_reply.started":"2023-02-05T06:29:00.983288Z","shell.execute_reply":"2023-02-05T06:30:37.875529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(model.state_dict(), './model.pt')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:37.879337Z","iopub.execute_input":"2023-02-05T06:30:37.879855Z","iopub.status.idle":"2023-02-05T06:30:38.168093Z","shell.execute_reply.started":"2023-02-05T06:30:37.879808Z","shell.execute_reply":"2023-02-05T06:30:38.166695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Data object and Loader\ndataset = MelanomaDataset(train_df, is_train=True, is_valid=False, is_test=False)\nloader = DataLoader(dataset,batch_size=1, shuffle=True)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.170033Z","iopub.execute_input":"2023-02-05T06:30:38.171308Z","iopub.status.idle":"2023-02-05T06:30:38.178635Z","shell.execute_reply.started":"2023-02-05T06:30:38.171261Z","shell.execute_reply":"2023-02-05T06:30:38.177139Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Get a sample\nfor image, label in test_loader:\n    image = torch.tensor(image, device=device, dtype=torch.float32)\n    label = torch.tensor(label, device=device, dtype=torch.float32)\n    out = model(image)\n    loss = criterion(out, label.unsqueeze(1))\n    pred = torch.sigmoid(out)\n    print('loss: ', loss)\n    print('Label:', label)\n    print('Pred:', pred)\n    break","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.180449Z","iopub.execute_input":"2023-02-05T06:30:38.181778Z","iopub.status.idle":"2023-02-05T06:30:38.315559Z","shell.execute_reply.started":"2023-02-05T06:30:38.181724Z","shell.execute_reply":"2023-02-05T06:30:38.314169Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'model.pt')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.317308Z","iopub.execute_input":"2023-02-05T06:30:38.318583Z","iopub.status.idle":"2023-02-05T06:30:38.328584Z","shell.execute_reply.started":"2023-02-05T06:30:38.318534Z","shell.execute_reply":"2023-02-05T06:30:38.327417Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_lo = ResNet34Network()\nmodel_lo = model_lo.to(device)\nmodel_lo.load_state_dict(torch.load('model.pt'))\nmodel_lo.eval()","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.330317Z","iopub.execute_input":"2023-02-05T06:30:38.330810Z","iopub.status.idle":"2023-02-05T06:30:38.878010Z","shell.execute_reply.started":"2023-02-05T06:30:38.330766Z","shell.execute_reply":"2023-02-05T06:30:38.876799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_df.loc[train_df['target']==1].head().values)","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.879880Z","iopub.execute_input":"2023-02-05T06:30:38.880423Z","iopub.status.idle":"2023-02-05T06:30:38.890593Z","shell.execute_reply.started":"2023-02-05T06:30:38.880381Z","shell.execute_reply":"2023-02-05T06:30:38.889200Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.columns","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.892257Z","iopub.execute_input":"2023-02-05T06:30:38.893092Z","iopub.status.idle":"2023-02-05T06:30:38.906674Z","shell.execute_reply.started":"2023-02-05T06:30:38.893042Z","shell.execute_reply":"2023-02-05T06:30:38.905319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Data object and Loader\ndf = pd.DataFrame({'image_name':['ISIC_2637011', 'ISIC_0149568'], 'patient_id':['IP_7279968', 'IP_0962375'], 'sex':['male', 'female'], 'age_approx':[45.0, 55.0],\n                  'anatom_site_general_challenge':['head/neck', 'upper extremity'], 'diagnosis':['unknown', 'melanoma'],\n                   'benign_malignant':['benign', 'malignant'], 'target':[0,1]})\n\n\ndataset = MelanomaDataset(df, is_train=True, is_valid=False, is_test=False)\nloader = DataLoader(dataset,batch_size=1, shuffle=False)\n# Get a sample\nfor image, label in loader:\n    image = torch.tensor(image, device=device, dtype=torch.float32)\n    label = torch.tensor(label, device=device, dtype=torch.float32)\n    out = model(image)\n    loss = criterion(out, label.unsqueeze(1))\n    pred = torch.sigmoid(out)\n    \n#     print('loss: ', loss)\n#     print('Label:', label)\n    print('Pred:', pred)\n    print('out:', torch.round(pred))\n    print('__________________________________________________________________')","metadata":{"execution":{"iopub.status.busy":"2023-02-05T06:30:38.908449Z","iopub.execute_input":"2023-02-05T06:30:38.909185Z","iopub.status.idle":"2023-02-05T06:30:40.275469Z","shell.execute_reply.started":"2023-02-05T06:30:38.909147Z","shell.execute_reply":"2023-02-05T06:30:40.274095Z"},"trusted":true},"execution_count":null,"outputs":[]}]}