Skip to content

cafe.method.CondaBackend

cafe.method.CondaBackend

Bases: Backend

Specific implementation of abstract Backend class using Python functions.

Source code in cafe/method/fate_conda_backend.py
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
class CondaBackend(Backend):
    """Specific implementation of abstract Backend class using Python functions."""

    # TODO: Here, the class is only for python methods, need to extend to R methods.

    def __init__(self, function_name="comp1", conda_name="cafe", id=""):
        self.function_name = function_name
        self.conda_name = conda_name
        self.id = id
        self.load_backend()

    def load_backend(self):
        logger.debug("load conda backend")
        if self.test_conda_env() is False:
            self.install_conda_env()

        cmd = f"conda run -n {self.conda_name} python --version"
        result = subprocess.run(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, timeout=10)
        if result.returncode != 0:
            logger.error(f"Conda environment '{self.conda_name}' not available: {result.stderr.strip()}")
            raise RuntimeError(f"Conda environment '{self.conda_name}' not available.")
        else:
            logger.debug(f"Conda environment '{self.conda_name}' is available: {result.stdout.strip()}", indent_level=2)

        # load function to get parameter
        self._load_function(self.function_name)

    def preprocess(self, adata: AnnData, parameters: dict, tmp_wd: str) -> None:
        """save adata h5ad, prior information and parameters json file in tmp_wd dir"""
        adata_filename = f"{tmp_wd}/adata.h5ad"
        adata.uns["filename"] = adata_filename  # save filename in uns for function use
        adata.write(filename=adata_filename)
        if settings.save_external_data or settings.save_h5ad:
            self.adata = adata  # need to save for comparison later

        with open(f"{tmp_wd}/parameters.json", "w") as f:
            json.dump(parameters, f)

    def execute(self, tmp_wd: str, benchmark_resource: False) -> dict:
        """conda run, save dict.pkl in tmp_wd dir, return trajectory_dict

        Args:
            tmp_wd (str): tmp working dir for docker mount and saving h5ad.h5, json file

        Returns:
            dict: trajectory dict
        """
        trajectory_dict = {}

        parse_args_script = f"{os.path.dirname(__file__)}/function/parse_args.py"

        # construct command
        cmd = f"""\
        python {parse_args_script} \
            --function_name={self.function_name} \
            --adata_path={tmp_wd}/adata.h5ad \
            --parameters={tmp_wd}/parameters.json \
            --output_filename={tmp_wd}/output.pkl \
        """  # tmp_wd is working dir
        if settings.save_external_data or settings.save_h5ad:
            cmd += f" --save_h5ad={tmp_wd}/output.h5ad"
        cmd = f"conda run -n {self.conda_name} --no-capture-output {cmd}"  # use conda environment to run
        if benchmark_resource:
            cmd = f"/usr/bin/time -v {cmd}"
        cmd = f"cd {tmp_wd} && {cmd}"  # set working dir, remove middle output files
        logger.debug(f"cmd: {cmd}")

        # Set environment variable for matplotlib to use a non-GUI backend
        env = os.environ.copy()
        env["MPLBACKEND"] = "Agg"

        # execuate command
        process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, env=env)
        # remove unimportant warning log
        stderr_lines = []  # to capture stderr for latter resource usage parsing
        threading.Thread(target=print_output(logger.debug), args=(process.stdout, "[conda-excute-stdout]"), daemon=True).start()
        threading.Thread(target=print_output(logger.debug, stderr_lines), args=(process.stderr, "[conda-excute-stderr]"), daemon=True).start()
        # wait for process
        process.wait()

        # read output pkl
        output_pkl_filename = f"{tmp_wd}/output.pkl"
        if not os.path.exists(output_pkl_filename):
            # no h5 file generated by docker, show error log
            logger.error("Conda error, no output.pkl generated by conda command!!!")
        else:
            logger.debug("Conda finish")
            with open(output_pkl_filename, "rb") as f:
                trajectory_dict = pickle.load(f)
            if settings.save_external_data:
                adata_new = sc.read_h5ad(f"{tmp_wd}/output.h5ad")  # read back adata if needed
                trajectory_dict["external_data"] = extract_external_data_dict_directly(self.adata, adata_new)
                logger.debug("save external data from adata after conda execution")
            if settings.save_h5ad:
                # save entire adata object in specific file.
                import shutil

                shutil.copyfile(f"{tmp_wd}/output.h5ad", f".cafe/{self.adata.uns['id']}/h5ad/{self.id}.h5ad")
            if benchmark_resource:
                # read usage string and transfer to dict
                usage_string = "".join(stderr_lines)
                logger.debug(f"resource usage string: {usage_string}")
                usage_dict = parse_bash_resource_usage_string(usage_string)
                logger.debug(f"resource usage dict: {usage_dict}")
                trajectory_dict["resource_usage"] = usage_dict
            return trajectory_dict

    def run(
        self,
        fadata: FateAnnData,
        parameters: dict,
    ):
        """run"""
        # check if benchmark resource from parameters.
        benchmark_resource = self._check_benchmark_resource(parameters)

        # prepare data and parameters
        adata = fadata.to_anndata(delete_trajectory=True)  # avoid other trajectory IO
        adata.uns["id"] = fadata.id
        parameters = self._get_parameters(fadata, parameters)

        # execute method, save input and output file in tmp dir
        with tempfile.TemporaryDirectory() as tmp_wd:
            logger.debug(f"Temp wd: {tmp_wd}")
            self.preprocess(adata, parameters, tmp_wd)

            trajectory_dict = self.execute(tmp_wd, benchmark_resource=benchmark_resource)

            fadata.add_trajectory_by_type(trajectory_dict)  # wrapper type sorted in trajectory dict help "add_trajectory_xxx" choice.

            # add resource usage if benchmark_resource is True
            if "resource_usage" in trajectory_dict:
                fadata.add_resource_usage(trajectory_dict["resource_usage"])

    # TOOD: consider if __call__ is needed
    # def __call__(self, adata: AnnData, rewrite: bool = True, **parameters):
    #     """simplified version for self.run"""
    #     # check if benchmark resource from parameters.
    #     benchmark_resource = False
    #     if "benchmark_resource" in parameters:
    #         benchmark_resource = parameters["benchmark_resource"]
    #         del parameters["benchmark_resource"]

    #     with tempfile.TemporaryDirectory() as tmp_wd:
    #         logger.debug(f"Temp wd: {tmp_wd}")
    #         self.preprocess(adata, {}, parameters, tmp_wd)
    #         trajectory_dict = self.execute(tmp_wd, benchmark_resource=benchmark_resource)

    #         return trajectory_dict

    def __str__(self):
        return f"CondaBackend: {self.function_name} in conda env '{self.conda_name}'"

    def test_conda_env(self):
        """test if conda environment is available"""
        try:
            result = subprocess.run(["conda", "env", "list"], capture_output=True, text=True, check=True, timeout=10)
            # The output contains a list of environments, one per line.
            # The name is usually the first word on the line.
            # We should ignore comment lines starting with '#'
            lines = result.stdout.splitlines()
            for line in lines:
                if line.startswith("#"):
                    continue
                # Split the line by whitespace and get the first element
                parts = line.split()
                if parts and parts[0] == self.conda_name:
                    # logger.debug(f"Conda environment '{self.conda_name}' found.", indent_level=2)
                    return True

            logger.warning(f"Conda environment '{self.conda_name}' not found.")
            return False
        except (subprocess.CalledProcessError, FileNotFoundError, subprocess.TimeoutExpired) as e:
            # FileNotFoundError if 'conda' command is not found
            # CalledProcessError if 'conda env list' returns a non-zero exit code
            logger.warning(f"Could not check for conda environments (is conda installed and in PATH?): {e}")
            return False

    def install_conda_env(self, max_waiting_time=600):
        """create environment by correspoding conda environment yml file"""
        env_file_path = os.path.join(os.path.dirname(__file__), "environment", f"{self.conda_name}.yaml")

        if not os.path.exists(env_file_path):
            logger.error(f"Conda environment yaml file not found at: {env_file_path}")
            raise FileNotFoundError(f"Conda environment yaml file not found for '{self.conda_name}'")

        logger.info(f"Creating conda environment '{self.conda_name}' from file: {env_file_path}")
        cmd = f"conda env create -f {env_file_path}"

        process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

        # Using threading to capture output in real-time
        stdout_thread = threading.Thread(target=print_output(logger.debug), args=(process.stdout, "[conda-create-stdout]"), daemon=True)
        stderr_thread = threading.Thread(target=print_output(logger.warning), args=(process.stderr, "[conda-create-stderr]"), daemon=True)
        stdout_thread.start()
        stderr_thread.start()

        process.wait()  # Wait for the subprocess to finish

        if process.returncode != 0:
            logger.error(f"failed to create conda environment '{self.conda_name}'.")
            # The stderr is already logged by the thread
            error_message = f"""
                Failed to create conda environment '{self.conda_name}'. Check logs for details.
                Try to manually create it using following command:
                '{cmd}'
            """
            raise RuntimeError(error_message)
        else:
            logger.info(f"successfully created conda environment '{self.conda_name}'.")

    def export_conda_env(self, export_dir: str = None, rewrite=False, format="yaml") -> None:
        # export conda environment to yml file  in 'environment'
        if self.conda_name == "cafe":
            logger.info("cafe conda env, don'n need to generate external conda environment file.")
            return

        if export_dir is None:
            export_dir = f"{os.path.dirname(__file__)}/environment"

        if format == "yml" or format == "yaml":
            # yaml file
            export_dir = export_dir if export_dir else f"{os.path.dirname(__file__)}/environment"  # yaml default dir in python packages
            export_filename = f"{export_dir}/{self.conda_name}.yaml"
            cmd = f"conda env export -n {self.conda_name} --no-builds > {export_filename}"
        else:
            # TODO: tar.gz file
            export_dir = export_dir if export_dir else "."  # tar.gz file must be saved in specified dir
            export_filename = f"{export_dir}/{self.conda_name}.tar.gz"
            cmd = f"conda pack -n {self.conda_name} -o {export_filename}"

        if os.path.exists(export_filename):
            if rewrite:
                logger.info(f"export conda environment file '{export_filename}' already exists, rewrite it.")
            else:
                logger.info(f"export conda environment file '{export_filename}' already exists, skip export.")
                return

        process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
        process.wait()  # very quick command, don't need reading log

        if os.path.exists(export_filename):
            logger.info(f"successfully export conda environment '{self.conda_name}' to '{export_filename}'")
        else:
            logger.error(f"failed to export conda environment '{self.conda_name}'.")
        # TODO: only need save key packages manually, delete build info and other unimportant info

    def generate_dockerfile(self, conda_env_dir: str = None, pip_requirement_dir: str = None, docker_env_dir: str = None) -> None:
        if self.conda_name == "cafe":
            logger.info("cafe conda env, can't generate dockerfile automatically, need to add it manually.")
            return

        #  read from conda yaml file and generate dockerfile automatically
        if conda_env_dir is None:
            conda_env_dir = os.path.join(os.path.dirname(__file__), "environment")
        if pip_requirement_dir is None:
            pip_requirement_dir = os.path.join(os.path.dirname(__file__), "requirement")
        if docker_env_dir is None:
            docker_env_dir = os.path.join(os.path.dirname(__file__), "Dockerfile")
        conda_env_filename = f"{conda_env_dir}/{self.function_name}.yaml"
        pip_requirement_filename = f"{pip_requirement_dir}/{self.function_name}.txt"
        docker_env_filename = f"{docker_env_dir}/{self.function_name}.dockerfile"

        with open(conda_env_filename, "r") as f:
            conda_env_dict = yaml.safe_load(f)

        # extract python version and pip packages
        python_version = "3.10.15"  # Default version
        git_needed = False
        gpu_needed = False
        for dep in conda_env_dict["dependencies"]:
            if isinstance(dep, str) and dep.startswith("python="):
                # Extract major.minor version, e.g., from 'python=3.10.18'
                python_version = dep.split("=")[1]
                logger.debug(f"detected python version: {python_version}")
            elif isinstance(dep, dict) and "pip" in dep.keys():
                pip_deps = dep["pip"]
                with open(f"{pip_requirement_filename}", "w") as f:
                    f.writelines([i + "\n" for i in pip_deps])
                    logger.debug(f"write pip requirements to '{pip_requirement_filename}'")
                if any(i.startswith("git+") for i in pip_deps):
                    git_needed = True
                if any("torch" in i or "tensorflow" in i for i in pip_deps):
                    gpu_needed = True

        # generate dockerfile from template
        with open(f"{docker_env_dir}/template.dockerfile", "r") as f:
            dockerfile_template = f.read()
        dockerfile_template = dockerfile_template.replace("$python_version", python_version)
        dockerfile_template = dockerfile_template.replace("$method_name", self.function_name)
        if git_needed:
            dockerfile_template = dockerfile_template.replace("# git installation if needed", "RUN apt-get update && apt-get install -y git")
        with open(docker_env_filename, "w") as f:
            f.write(dockerfile_template)
            logger.info(f"write dockerfile base template.dockerfile to '{docker_env_filename}'")

        #  if torch or tensorflow in packages, use choosing corresponding cuda base image carefully
        if gpu_needed:
            logger.warning("GPU packages detected, please ensure to choose appropriate CUDA base image in the generated Dockerfile.")

    def build_docker_image(self) -> None:
        # TODO: build docker image from generated dockerfile
        pass

execute(tmp_wd, benchmark_resource)

conda run, save dict.pkl in tmp_wd dir, return trajectory_dict

Parameters:

Name Type Description Default
tmp_wd str

tmp working dir for docker mount and saving h5ad.h5, json file

required

Returns:

Name Type Description
dict dict

trajectory dict

Source code in cafe/method/fate_conda_backend.py
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
def execute(self, tmp_wd: str, benchmark_resource: False) -> dict:
    """conda run, save dict.pkl in tmp_wd dir, return trajectory_dict

    Args:
        tmp_wd (str): tmp working dir for docker mount and saving h5ad.h5, json file

    Returns:
        dict: trajectory dict
    """
    trajectory_dict = {}

    parse_args_script = f"{os.path.dirname(__file__)}/function/parse_args.py"

    # construct command
    cmd = f"""\
    python {parse_args_script} \
        --function_name={self.function_name} \
        --adata_path={tmp_wd}/adata.h5ad \
        --parameters={tmp_wd}/parameters.json \
        --output_filename={tmp_wd}/output.pkl \
    """  # tmp_wd is working dir
    if settings.save_external_data or settings.save_h5ad:
        cmd += f" --save_h5ad={tmp_wd}/output.h5ad"
    cmd = f"conda run -n {self.conda_name} --no-capture-output {cmd}"  # use conda environment to run
    if benchmark_resource:
        cmd = f"/usr/bin/time -v {cmd}"
    cmd = f"cd {tmp_wd} && {cmd}"  # set working dir, remove middle output files
    logger.debug(f"cmd: {cmd}")

    # Set environment variable for matplotlib to use a non-GUI backend
    env = os.environ.copy()
    env["MPLBACKEND"] = "Agg"

    # execuate command
    process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, env=env)
    # remove unimportant warning log
    stderr_lines = []  # to capture stderr for latter resource usage parsing
    threading.Thread(target=print_output(logger.debug), args=(process.stdout, "[conda-excute-stdout]"), daemon=True).start()
    threading.Thread(target=print_output(logger.debug, stderr_lines), args=(process.stderr, "[conda-excute-stderr]"), daemon=True).start()
    # wait for process
    process.wait()

    # read output pkl
    output_pkl_filename = f"{tmp_wd}/output.pkl"
    if not os.path.exists(output_pkl_filename):
        # no h5 file generated by docker, show error log
        logger.error("Conda error, no output.pkl generated by conda command!!!")
    else:
        logger.debug("Conda finish")
        with open(output_pkl_filename, "rb") as f:
            trajectory_dict = pickle.load(f)
        if settings.save_external_data:
            adata_new = sc.read_h5ad(f"{tmp_wd}/output.h5ad")  # read back adata if needed
            trajectory_dict["external_data"] = extract_external_data_dict_directly(self.adata, adata_new)
            logger.debug("save external data from adata after conda execution")
        if settings.save_h5ad:
            # save entire adata object in specific file.
            import shutil

            shutil.copyfile(f"{tmp_wd}/output.h5ad", f".cafe/{self.adata.uns['id']}/h5ad/{self.id}.h5ad")
        if benchmark_resource:
            # read usage string and transfer to dict
            usage_string = "".join(stderr_lines)
            logger.debug(f"resource usage string: {usage_string}")
            usage_dict = parse_bash_resource_usage_string(usage_string)
            logger.debug(f"resource usage dict: {usage_dict}")
            trajectory_dict["resource_usage"] = usage_dict
        return trajectory_dict

install_conda_env(max_waiting_time=600)

create environment by correspoding conda environment yml file

Source code in cafe/method/fate_conda_backend.py
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
def install_conda_env(self, max_waiting_time=600):
    """create environment by correspoding conda environment yml file"""
    env_file_path = os.path.join(os.path.dirname(__file__), "environment", f"{self.conda_name}.yaml")

    if not os.path.exists(env_file_path):
        logger.error(f"Conda environment yaml file not found at: {env_file_path}")
        raise FileNotFoundError(f"Conda environment yaml file not found for '{self.conda_name}'")

    logger.info(f"Creating conda environment '{self.conda_name}' from file: {env_file_path}")
    cmd = f"conda env create -f {env_file_path}"

    process = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

    # Using threading to capture output in real-time
    stdout_thread = threading.Thread(target=print_output(logger.debug), args=(process.stdout, "[conda-create-stdout]"), daemon=True)
    stderr_thread = threading.Thread(target=print_output(logger.warning), args=(process.stderr, "[conda-create-stderr]"), daemon=True)
    stdout_thread.start()
    stderr_thread.start()

    process.wait()  # Wait for the subprocess to finish

    if process.returncode != 0:
        logger.error(f"failed to create conda environment '{self.conda_name}'.")
        # The stderr is already logged by the thread
        error_message = f"""
            Failed to create conda environment '{self.conda_name}'. Check logs for details.
            Try to manually create it using following command:
            '{cmd}'
        """
        raise RuntimeError(error_message)
    else:
        logger.info(f"successfully created conda environment '{self.conda_name}'.")

preprocess(adata, parameters, tmp_wd)

save adata h5ad, prior information and parameters json file in tmp_wd dir

Source code in cafe/method/fate_conda_backend.py
47
48
49
50
51
52
53
54
55
56
def preprocess(self, adata: AnnData, parameters: dict, tmp_wd: str) -> None:
    """save adata h5ad, prior information and parameters json file in tmp_wd dir"""
    adata_filename = f"{tmp_wd}/adata.h5ad"
    adata.uns["filename"] = adata_filename  # save filename in uns for function use
    adata.write(filename=adata_filename)
    if settings.save_external_data or settings.save_h5ad:
        self.adata = adata  # need to save for comparison later

    with open(f"{tmp_wd}/parameters.json", "w") as f:
        json.dump(parameters, f)

run(fadata, parameters)

run

Source code in cafe/method/fate_conda_backend.py
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
def run(
    self,
    fadata: FateAnnData,
    parameters: dict,
):
    """run"""
    # check if benchmark resource from parameters.
    benchmark_resource = self._check_benchmark_resource(parameters)

    # prepare data and parameters
    adata = fadata.to_anndata(delete_trajectory=True)  # avoid other trajectory IO
    adata.uns["id"] = fadata.id
    parameters = self._get_parameters(fadata, parameters)

    # execute method, save input and output file in tmp dir
    with tempfile.TemporaryDirectory() as tmp_wd:
        logger.debug(f"Temp wd: {tmp_wd}")
        self.preprocess(adata, parameters, tmp_wd)

        trajectory_dict = self.execute(tmp_wd, benchmark_resource=benchmark_resource)

        fadata.add_trajectory_by_type(trajectory_dict)  # wrapper type sorted in trajectory dict help "add_trajectory_xxx" choice.

        # add resource usage if benchmark_resource is True
        if "resource_usage" in trajectory_dict:
            fadata.add_resource_usage(trajectory_dict["resource_usage"])

test_conda_env()

test if conda environment is available

Source code in cafe/method/fate_conda_backend.py
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
def test_conda_env(self):
    """test if conda environment is available"""
    try:
        result = subprocess.run(["conda", "env", "list"], capture_output=True, text=True, check=True, timeout=10)
        # The output contains a list of environments, one per line.
        # The name is usually the first word on the line.
        # We should ignore comment lines starting with '#'
        lines = result.stdout.splitlines()
        for line in lines:
            if line.startswith("#"):
                continue
            # Split the line by whitespace and get the first element
            parts = line.split()
            if parts and parts[0] == self.conda_name:
                # logger.debug(f"Conda environment '{self.conda_name}' found.", indent_level=2)
                return True

        logger.warning(f"Conda environment '{self.conda_name}' not found.")
        return False
    except (subprocess.CalledProcessError, FileNotFoundError, subprocess.TimeoutExpired) as e:
        # FileNotFoundError if 'conda' command is not found
        # CalledProcessError if 'conda env list' returns a non-zero exit code
        logger.warning(f"Could not check for conda environments (is conda installed and in PATH?): {e}")
        return False