{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-01-31T16:52:33.285377Z","iopub.execute_input":"2023-01-31T16:52:33.286290Z","iopub.status.idle":"2023-01-31T16:52:34.308223Z","shell.execute_reply.started":"2023-01-31T16:52:33.286165Z","shell.execute_reply":"2023-01-31T16:52:34.307063Z"},"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')\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.309932Z","iopub.execute_input":"2023-01-31T16:52:34.310239Z","iopub.status.idle":"2023-01-31T16:52:34.480479Z","shell.execute_reply.started":"2023-01-31T16:52:34.310212Z","shell.execute_reply":"2023-01-31T16:52:34.479298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.482268Z","iopub.execute_input":"2023-01-31T16:52:34.482720Z","iopub.status.idle":"2023-01-31T16:52:34.512080Z","shell.execute_reply.started":"2023-01-31T16:52:34.482664Z","shell.execute_reply":"2023-01-31T16:52:34.511221Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.shape","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.514209Z","iopub.execute_input":"2023-01-31T16:52:34.514751Z","iopub.status.idle":"2023-01-31T16:52:34.520858Z","shell.execute_reply.started":"2023-01-31T16:52:34.514697Z","shell.execute_reply":"2023-01-31T16:52:34.519730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.522376Z","iopub.execute_input":"2023-01-31T16:52:34.522759Z","iopub.status.idle":"2023-01-31T16:52:34.560266Z","shell.execute_reply.started":"2023-01-31T16:52:34.522719Z","shell.execute_reply":"2023-01-31T16:52:34.558918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.describe()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.561626Z","iopub.execute_input":"2023-01-31T16:52:34.561968Z","iopub.status.idle":"2023-01-31T16:52:34.589173Z","shell.execute_reply.started":"2023-01-31T16:52:34.561936Z","shell.execute_reply":"2023-01-31T16:52:34.587868Z"},"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\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:34.590746Z","iopub.execute_input":"2023-01-31T16:52:34.591255Z","iopub.status.idle":"2023-01-31T16:52:34.946718Z","shell.execute_reply.started":"2023-01-31T16:52:34.591211Z","shell.execute_reply":"2023-01-31T16:52:34.945813Z"},"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":"2023-01-31T16:52:34.948033Z","iopub.execute_input":"2023-01-31T16:52:34.948543Z","iopub.status.idle":"2023-01-31T16:52:35.174751Z","shell.execute_reply.started":"2023-01-31T16:52:34.948507Z","shell.execute_reply":"2023-01-31T16:52:35.173672Z"},"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":"2023-01-31T16:52:35.176143Z","iopub.execute_input":"2023-01-31T16:52:35.176976Z","iopub.status.idle":"2023-01-31T16:52:35.493884Z","shell.execute_reply.started":"2023-01-31T16:52:35.176943Z","shell.execute_reply":"2023-01-31T16:52:35.492742Z"},"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":"2023-01-31T16:52:35.498402Z","iopub.execute_input":"2023-01-31T16:52:35.498798Z","iopub.status.idle":"2023-01-31T16:52:35.727994Z","shell.execute_reply.started":"2023-01-31T16:52:35.498762Z","shell.execute_reply":"2023-01-31T16:52:35.726899Z"},"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":"2023-01-31T16:52:35.729414Z","iopub.execute_input":"2023-01-31T16:52:35.731015Z","iopub.status.idle":"2023-01-31T16:52:36.048985Z","shell.execute_reply.started":"2023-01-31T16:52:35.730969Z","shell.execute_reply":"2023-01-31T16:52:36.047831Z"},"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\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:36.050221Z","iopub.execute_input":"2023-01-31T16:52:36.050557Z","iopub.status.idle":"2023-01-31T16:52:36.072930Z","shell.execute_reply.started":"2023-01-31T16:52:36.050524Z","shell.execute_reply":"2023-01-31T16:52:36.071775Z"},"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":"2023-01-31T16:52:36.074530Z","iopub.execute_input":"2023-01-31T16:52:36.074906Z","iopub.status.idle":"2023-01-31T16:52:36.093862Z","shell.execute_reply.started":"2023-01-31T16:52:36.074873Z","shell.execute_reply":"2023-01-31T16:52:36.092679Z"},"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":"2023-01-31T16:52:36.095084Z","iopub.execute_input":"2023-01-31T16:52:36.095422Z","iopub.status.idle":"2023-01-31T16:52:36.109656Z","shell.execute_reply.started":"2023-01-31T16:52:36.095389Z","shell.execute_reply":"2023-01-31T16:52:36.108321Z"},"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":"2023-01-31T16:52:36.112494Z","iopub.execute_input":"2023-01-31T16:52:36.113426Z","iopub.status.idle":"2023-01-31T16:52:36.125123Z","shell.execute_reply.started":"2023-01-31T16:52:36.113375Z","shell.execute_reply":"2023-01-31T16:52:36.123876Z"},"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":"2023-01-31T16:52:36.127195Z","iopub.execute_input":"2023-01-31T16:52:36.128190Z","iopub.status.idle":"2023-01-31T16:52:36.529654Z","shell.execute_reply.started":"2023-01-31T16:52:36.128142Z","shell.execute_reply":"2023-01-31T16:52:36.528260Z"},"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":"2023-01-31T16:52:36.535906Z","iopub.execute_input":"2023-01-31T16:52:36.540019Z","iopub.status.idle":"2023-01-31T16:52:36.583425Z","shell.execute_reply.started":"2023-01-31T16:52:36.539949Z","shell.execute_reply":"2023-01-31T16:52:36.581972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.shape","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:36.585332Z","iopub.execute_input":"2023-01-31T16:52:36.586040Z","iopub.status.idle":"2023-01-31T16:52:36.592859Z","shell.execute_reply.started":"2023-01-31T16:52:36.585994Z","shell.execute_reply":"2023-01-31T16:52:36.591790Z"},"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":"2023-01-31T16:52:36.594285Z","iopub.execute_input":"2023-01-31T16:52:36.599327Z","iopub.status.idle":"2023-01-31T16:52:36.611386Z","shell.execute_reply.started":"2023-01-31T16:52:36.599290Z","shell.execute_reply":"2023-01-31T16:52:36.610429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#how many unique patients are there anyway?\nn_patients = len(pd.unique(train['patient_id']))\n\nprint('There are {} unique patients in the training set'.format(n_patients))\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:36.612667Z","iopub.execute_input":"2023-01-31T16:52:36.615510Z","iopub.status.idle":"2023-01-31T16:52:36.626065Z","shell.execute_reply.started":"2023-01-31T16:52:36.615458Z","shell.execute_reply":"2023-01-31T16:52:36.624757Z"},"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":"2023-01-31T16:52:36.628468Z","iopub.execute_input":"2023-01-31T16:52:36.628897Z","iopub.status.idle":"2023-01-31T16:52:36.666990Z","shell.execute_reply.started":"2023-01-31T16:52:36.628858Z","shell.execute_reply":"2023-01-31T16:52:36.665827Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print summary stats for the number of images per patient.\nindividuals_count.image_name.describe()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:36.668630Z","iopub.execute_input":"2023-01-31T16:52:36.669393Z","iopub.status.idle":"2023-01-31T16:52:36.682464Z","shell.execute_reply.started":"2023-01-31T16:52:36.669347Z","shell.execute_reply":"2023-01-31T16:52:36.680758Z"},"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":"2023-01-31T16:52:36.684170Z","iopub.execute_input":"2023-01-31T16:52:36.684589Z","iopub.status.idle":"2023-01-31T16:52:37.108399Z","shell.execute_reply.started":"2023-01-31T16:52:36.684555Z","shell.execute_reply":"2023-01-31T16:52:37.107125Z"},"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":"2023-01-31T16:52:37.110366Z","iopub.execute_input":"2023-01-31T16:52:37.111188Z","iopub.status.idle":"2023-01-31T16:52:37.121101Z","shell.execute_reply.started":"2023-01-31T16:52:37.111127Z","shell.execute_reply":"2023-01-31T16:52:37.119867Z"},"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":"2023-01-31T16:52:37.122594Z","iopub.execute_input":"2023-01-31T16:52:37.123663Z","iopub.status.idle":"2023-01-31T16:52:37.431956Z","shell.execute_reply.started":"2023-01-31T16:52:37.123615Z","shell.execute_reply":"2023-01-31T16:52:37.430777Z"},"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'])]\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:37.433921Z","iopub.execute_input":"2023-01-31T16:52:37.434390Z","iopub.status.idle":"2023-01-31T16:52:37.450724Z","shell.execute_reply.started":"2023-01-31T16:52:37.434345Z","shell.execute_reply":"2023-01-31T16:52:37.449234Z"},"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":"2023-01-31T16:52:37.452517Z","iopub.execute_input":"2023-01-31T16:52:37.453056Z","iopub.status.idle":"2023-01-31T16:52:37.470254Z","shell.execute_reply.started":"2023-01-31T16:52:37.453011Z","shell.execute_reply":"2023-01-31T16:52:37.469060Z"},"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":"2023-01-31T16:52:37.479964Z","iopub.execute_input":"2023-01-31T16:52:37.480333Z","iopub.status.idle":"2023-01-31T16:52:37.487406Z","shell.execute_reply.started":"2023-01-31T16:52:37.480301Z","shell.execute_reply":"2023-01-31T16:52:37.486213Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"These particular patients don't contribute any data to the imbalanced target class. They also represent just 0.21% of the overall data. Time to say goodbye for good!","metadata":{}},{"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":"2023-01-31T16:52:37.488798Z","iopub.execute_input":"2023-01-31T16:52:37.489214Z","iopub.status.idle":"2023-01-31T16:52:37.517690Z","shell.execute_reply.started":"2023-01-31T16:52:37.489169Z","shell.execute_reply":"2023-01-31T16:52:37.516406Z"},"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":"2023-01-31T16:52:37.519216Z","iopub.execute_input":"2023-01-31T16:52:37.519579Z","iopub.status.idle":"2023-01-31T16:52:37.539831Z","shell.execute_reply.started":"2023-01-31T16:52:37.519546Z","shell.execute_reply":"2023-01-31T16:52:37.538741Z"},"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":"2023-01-31T16:52:37.541063Z","iopub.execute_input":"2023-01-31T16:52:37.541403Z","iopub.status.idle":"2023-01-31T16:52:37.546725Z","shell.execute_reply.started":"2023-01-31T16:52:37.541371Z","shell.execute_reply":"2023-01-31T16:52:37.545612Z"},"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',\t'age_approx_sum'], inplace=True)\npatients.rename(columns={'image_name':'n_images'}, inplace=True)\npatients.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:37.548181Z","iopub.execute_input":"2023-01-31T16:52:37.548538Z","iopub.status.idle":"2023-01-31T16:52:37.571655Z","shell.execute_reply.started":"2023-01-31T16:52:37.548506Z","shell.execute_reply":"2023-01-31T16:52:37.570125Z"},"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":"2023-01-31T16:52:37.573439Z","iopub.execute_input":"2023-01-31T16:52:37.573829Z","iopub.status.idle":"2023-01-31T16:52:37.603729Z","shell.execute_reply.started":"2023-01-31T16:52:37.573794Z","shell.execute_reply":"2023-01-31T16:52:37.602506Z"},"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',\t'benign_malignant',\t'target'], inplace=True)\npatients.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:37.605684Z","iopub.execute_input":"2023-01-31T16:52:37.606101Z","iopub.status.idle":"2023-01-31T16:52:37.637885Z","shell.execute_reply.started":"2023-01-31T16:52:37.606063Z","shell.execute_reply":"2023-01-31T16:52:37.636769Z"},"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":"2023-01-31T16:52:37.639488Z","iopub.execute_input":"2023-01-31T16:52:37.639859Z","iopub.status.idle":"2023-01-31T16:52:38.128526Z","shell.execute_reply.started":"2023-01-31T16:52:37.639827Z","shell.execute_reply":"2023-01-31T16:52:38.127318Z"},"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":"2023-01-31T16:52:38.130056Z","iopub.execute_input":"2023-01-31T16:52:38.130421Z","iopub.status.idle":"2023-01-31T16:52:38.524035Z","shell.execute_reply.started":"2023-01-31T16:52:38.130387Z","shell.execute_reply":"2023-01-31T16:52:38.522759Z"},"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')\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:38.525320Z","iopub.execute_input":"2023-01-31T16:52:38.526415Z","iopub.status.idle":"2023-01-31T16:52:38.760719Z","shell.execute_reply.started":"2023-01-31T16:52:38.526363Z","shell.execute_reply":"2023-01-31T16:52:38.759390Z"},"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":"2023-01-31T16:52:38.762165Z","iopub.execute_input":"2023-01-31T16:52:38.762592Z","iopub.status.idle":"2023-01-31T16:52:39.196246Z","shell.execute_reply.started":"2023-01-31T16:52:38.762556Z","shell.execute_reply":"2023-01-31T16:52:39.194912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"A spectrum of target_sum values were found across all the ages included in the image dataset, with the exception of the 10year olds.","metadata":{}},{"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')\n","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:39.197548Z","iopub.execute_input":"2023-01-31T16:52:39.197913Z","iopub.status.idle":"2023-01-31T16:52:39.508223Z","shell.execute_reply.started":"2023-01-31T16:52:39.197880Z","shell.execute_reply":"2023-01-31T16:52:39.507027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Visualizing Images**","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')\nplt.show()\n\n#print metadata\nprint(im.meta.keys())","metadata":{"execution":{"iopub.status.busy":"2023-01-31T16:52:39.509681Z","iopub.execute_input":"2023-01-31T16:52:39.510154Z","iopub.status.idle":"2023-01-31T16:52:43.779571Z","shell.execute_reply.started":"2023-01-31T16:52:39.510108Z","shell.execute_reply":"2023-01-31T16:52:43.778400Z"},"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":"2023-01-31T16:52:43.780933Z","iopub.execute_input":"2023-01-31T16:52:43.781252Z","iopub.status.idle":"2023-01-31T16:52:43.788795Z","shell.execute_reply.started":"2023-01-31T16:52:43.781223Z","shell.execute_reply":"2023-01-31T16:52:43.787581Z"},"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":"2023-01-31T16:52:43.790231Z","iopub.execute_input":"2023-01-31T16:52:43.790882Z"},"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":{"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.idle":"2023-01-31T17:10:14.012062Z","shell.execute_reply.started":"2023-01-31T17:06:28.271474Z","shell.execute_reply":"2023-01-31T17:10:14.010751Z"},"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":"2023-01-31T17:10:14.014042Z","iopub.execute_input":"2023-01-31T17:10:14.014416Z","iopub.status.idle":"2023-01-31T17:10:17.746431Z","shell.execute_reply.started":"2023-01-31T17:10:14.014381Z","shell.execute_reply":"2023-01-31T17:10:17.745112Z"},"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":"2023-01-31T17:10:17.747615Z","iopub.execute_input":"2023-01-31T17:10:17.748244Z","iopub.status.idle":"2023-01-31T17:10:17.756359Z","shell.execute_reply.started":"2023-01-31T17:10:17.748209Z","shell.execute_reply":"2023-01-31T17:10:17.755411Z"},"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":"2023-01-31T17:10:17.757552Z","iopub.execute_input":"2023-01-31T17:10:17.759392Z","iopub.status.idle":"2023-01-31T17:10:17.767402Z","shell.execute_reply.started":"2023-01-31T17:10:17.759346Z","shell.execute_reply":"2023-01-31T17:10:17.766438Z"},"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":"2023-01-31T17:10:17.768953Z","iopub.execute_input":"2023-01-31T17:10:17.769639Z","iopub.status.idle":"2023-01-31T17:10:17.820384Z","shell.execute_reply.started":"2023-01-31T17:10:17.769596Z","shell.execute_reply":"2023-01-31T17:10:17.819329Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.target.value_counts()","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:17.821771Z","iopub.execute_input":"2023-01-31T17:10:17.822135Z","iopub.status.idle":"2023-01-31T17:10:17.831054Z","shell.execute_reply.started":"2023-01-31T17:10:17.822103Z","shell.execute_reply":"2023-01-31T17:10:17.829883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(train_df)","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:17.832257Z","iopub.execute_input":"2023-01-31T17:10:17.833279Z","iopub.status.idle":"2023-01-31T17:10:17.842946Z","shell.execute_reply.started":"2023-01-31T17:10:17.833244Z","shell.execute_reply":"2023-01-31T17:10:17.841634Z"},"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":"2023-01-31T17:10:17.844784Z","iopub.execute_input":"2023-01-31T17:10:17.845231Z","iopub.status.idle":"2023-01-31T17:10:17.857744Z","shell.execute_reply.started":"2023-01-31T17:10:17.845177Z","shell.execute_reply":"2023-01-31T17:10:17.856458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(resnet34(pretrained=True))","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:17.859305Z","iopub.execute_input":"2023-01-31T17:10:17.859895Z","iopub.status.idle":"2023-01-31T17:10:27.682200Z","shell.execute_reply.started":"2023-01-31T17:10:17.859849Z","shell.execute_reply":"2023-01-31T17:10:27.680803Z"},"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":"2023-01-31T17:10:27.684131Z","iopub.execute_input":"2023-01-31T17:10:27.684595Z","iopub.status.idle":"2023-01-31T17:10:27.694160Z","shell.execute_reply.started":"2023-01-31T17:10:27.684548Z","shell.execute_reply":"2023-01-31T17:10:27.692002Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = ResNet34Network()\nmodel = model.to(device)","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:27.695815Z","iopub.execute_input":"2023-01-31T17:10:27.696446Z","iopub.status.idle":"2023-01-31T17:10:28.111423Z","shell.execute_reply.started":"2023-01-31T17:10:27.696410Z","shell.execute_reply":"2023-01-31T17:10:28.110236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(model)","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:28.113233Z","iopub.execute_input":"2023-01-31T17:10:28.113603Z","iopub.status.idle":"2023-01-31T17:10:28.119645Z","shell.execute_reply.started":"2023-01-31T17:10:28.113565Z","shell.execute_reply":"2023-01-31T17:10:28.118776Z"},"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":"2023-01-31T17:10:28.120896Z","iopub.execute_input":"2023-01-31T17:10:28.121391Z","iopub.status.idle":"2023-01-31T17:10:28.131568Z","shell.execute_reply.started":"2023-01-31T17:10:28.121359Z","shell.execute_reply":"2023-01-31T17:10:28.130454Z"},"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)","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:10:28.132896Z","iopub.execute_input":"2023-01-31T17:10:28.133831Z","iopub.status.idle":"2023-01-31T17:10:28.657692Z","shell.execute_reply.started":"2023-01-31T17:10:28.133796Z","shell.execute_reply":"2023-01-31T17:10:28.656776Z"},"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":"2023-01-31T17:10:28.658873Z","iopub.execute_input":"2023-01-31T17:10:28.659483Z","iopub.status.idle":"2023-01-31T17:10:28.665822Z","shell.execute_reply.started":"2023-01-31T17:10:28.659442Z","shell.execute_reply":"2023-01-31T17:10:28.664537Z"},"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":"2023-01-31T17:10:28.667409Z","iopub.execute_input":"2023-01-31T17:10:28.667766Z","iopub.status.idle":"2023-01-31T17:10:28.682478Z","shell.execute_reply.started":"2023-01-31T17:10:28.667729Z","shell.execute_reply":"2023-01-31T17:10:28.681278Z"},"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":"2023-01-31T17:10:28.684524Z","iopub.execute_input":"2023-01-31T17:10:28.685003Z","iopub.status.idle":"2023-01-31T17:10:28.693178Z","shell.execute_reply.started":"2023-01-31T17:10:28.684957Z","shell.execute_reply":"2023-01-31T17:10:28.691883Z"},"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":"2023-01-31T17:10:28.695189Z","iopub.execute_input":"2023-01-31T17:10:28.695939Z","iopub.status.idle":"2023-01-31T17:10:28.708409Z","shell.execute_reply.started":"2023-01-31T17:10:28.695892Z","shell.execute_reply":"2023-01-31T17:10:28.707293Z"},"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        # 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":"2023-01-31T17:10:28.710239Z","iopub.execute_input":"2023-01-31T17:10:28.710970Z","iopub.status.idle":"2023-01-31T17:36:01.152529Z","shell.execute_reply.started":"2023-01-31T17:10:28.710923Z","shell.execute_reply":"2023-01-31T17:36:01.150506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(model.state_dict(), './model.pt')","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:36:01.155042Z","iopub.execute_input":"2023-01-31T17:36:01.155482Z","iopub.status.idle":"2023-01-31T17:36:01.446960Z","shell.execute_reply.started":"2023-01-31T17:36:01.155437Z","shell.execute_reply":"2023-01-31T17:36:01.445596Z"},"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":"2023-01-31T17:36:01.448458Z","iopub.execute_input":"2023-01-31T17:36:01.449395Z","iopub.status.idle":"2023-01-31T17:36:01.454830Z","shell.execute_reply.started":"2023-01-31T17:36:01.449356Z","shell.execute_reply":"2023-01-31T17:36:01.453769Z"},"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":"2023-01-31T17:36:01.456264Z","iopub.execute_input":"2023-01-31T17:36:01.456804Z","iopub.status.idle":"2023-01-31T17:36:01.611389Z","shell.execute_reply.started":"2023-01-31T17:36:01.456764Z","shell.execute_reply":"2023-01-31T17:36:01.610292Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'model.pt')","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:36:01.612611Z","iopub.execute_input":"2023-01-31T17:36:01.612963Z","iopub.status.idle":"2023-01-31T17:36:01.621017Z","shell.execute_reply.started":"2023-01-31T17:36:01.612932Z","shell.execute_reply":"2023-01-31T17:36:01.619579Z"},"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":"2023-01-31T17:36:01.622898Z","iopub.execute_input":"2023-01-31T17:36:01.623735Z","iopub.status.idle":"2023-01-31T17:36:02.140845Z","shell.execute_reply.started":"2023-01-31T17:36:01.623648Z","shell.execute_reply":"2023-01-31T17:36:02.139474Z"},"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":"2023-01-31T17:36:02.142620Z","iopub.execute_input":"2023-01-31T17:36:02.143560Z","iopub.status.idle":"2023-01-31T17:36:02.153371Z","shell.execute_reply.started":"2023-01-31T17:36:02.143496Z","shell.execute_reply":"2023-01-31T17:36:02.152146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.columns","metadata":{"execution":{"iopub.status.busy":"2023-01-31T17:36:02.155156Z","iopub.execute_input":"2023-01-31T17:36:02.155655Z","iopub.status.idle":"2023-01-31T17:36:02.168057Z","shell.execute_reply.started":"2023-01-31T17:36:02.155606Z","shell.execute_reply":"2023-01-31T17:36:02.166695Z"},"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":"2023-01-31T17:36:02.169629Z","iopub.execute_input":"2023-01-31T17:36:02.170368Z","iopub.status.idle":"2023-01-31T17:36:03.464167Z","shell.execute_reply.started":"2023-01-31T17:36:02.170329Z","shell.execute_reply":"2023-01-31T17:36:03.463211Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}